---
title: "DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning"
description: "DeepSeek-R1 exposes its reasoning, so the authors use it to launch a research programme they call… 143 references, cited by 47 papers here."
authors: ["Sara Vera Marjanovic", "Arkil Patel", "Vaibhav Adlakha", "Milad Aghajohari", "Parishad BehnamGhader", "Mehar Bhatia", "Aditi Khandelwal", "Austin Kraft", "Benno Krojer", "Xing Han Lu", "Nicholas Meade", "Dongchan Shin", "Amirhossein Kazemnejad", "Gaurav Kamath", "Marius Mosbach", "Karolina Stanczak", "Siva Reddy"]
year: 2025
venue: "arXiv:2504.07128"
source: "https://arxiv.org/abs/2504.07128"
doi: "10.48550/arxiv.2504.07128"
arxiv: "2504.07128"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/marjanovic-2025-deepseek-r1-thoughtology-let-s/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/marjanovic-2025-deepseek-r1-thoughtology-let-s/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning

# DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning

**Authors:** [Sara Vera Marjanovic](https://md.research.elamur.ai/free/en/authors/sara-vera-marjanovic/), [Arkil Patel](https://md.research.elamur.ai/free/en/authors/arkil-patel/), [Vaibhav Adlakha](https://md.research.elamur.ai/free/en/authors/vaibhav-adlakha/), [Milad Aghajohari](https://md.research.elamur.ai/free/en/authors/milad-aghajohari/), [Parishad BehnamGhader](https://md.research.elamur.ai/free/en/authors/parishad-behnamghader/), [Mehar Bhatia](https://md.research.elamur.ai/free/en/authors/mehar-bhatia/), Aditi Khandelwal, Austin Kraft, [Benno Krojer](https://md.research.elamur.ai/free/en/authors/benno-krojer/), [Xing Han Lu](https://md.research.elamur.ai/free/en/authors/xing-han-lu/), [Nicholas Meade](https://md.research.elamur.ai/free/en/authors/nicholas-meade/), [Dongchan Shin](https://md.research.elamur.ai/free/en/authors/dongchan-shin/), [Amirhossein Kazemnejad](https://md.research.elamur.ai/free/en/authors/amirhossein-kazemnejad/), Gaurav Kamath, [Marius Mosbach](https://md.research.elamur.ai/free/en/authors/marius-mosbach/), [Karolina Stanczak](https://md.research.elamur.ai/free/en/authors/karolina-stanczak/) and [Siva Reddy](https://md.research.elamur.ai/free/en/authors/siva-reddy/) · **Year:** 2025 · **Venue:** arXiv:2504.07128 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2504.07128) · [PDF](https://arxiv.org/pdf/2504.07128) · [DOI 10.48550/arxiv.2504.07128](https://doi.org/10.48550/arxiv.2504.07128) · [arXiv 2504.07128](https://arxiv.org/abs/2504.07128) · [OpenAlex](https://openalex.org/W6948163397)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [47](https://md.research.elamur.ai/free/en/papers/marjanovic-2025-deepseek-r1-thoughtology-let-s/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary

Large Reasoning Models (LRMs) produce long reasoning chains before giving an answer. Their internal behaviour has been hard to study because OpenAI's o1 hides its thoughts. DeepSeek-R1 exposes its reasoning, so the authors use it to launch a research programme they call "Thoughtology."

They first build a taxonomy of the phases R1 moves through while reasoning. They then run targeted experiments on several questions:

- how thought length affects accuracy, and whether it can be controlled;
- how R1 handles long, conflicting or misleading contexts;
- safety and moral or cultural behaviour across languages;
- parallels with human sentence processing;
- visual and physical world modelling.

The results are mixed. Each problem seems to have an optimal reasoning length, and thinking beyond it lowers accuracy. R1 also cannot regulate its own thought length. It often "ruminates," returning to framings it has already tried instead of exploring new ones. It is less safe than DeepSeek-V3, and it can be used to write jailbreaks against other aligned models.

These findings matter because longer inference-time reasoning is often assumed to help. The study shows its limits and points to concrete targets for improving LRMs.

## Key points

- **Reasoning structure:** R1's thoughts follow a recurring pattern. It defines the problem, decomposes it toward an interim solution, then repeats reconstruction and verification cycles, which often lack diversity.
- **Thought length:** Experiments on AIME-24, GSM8K, multidigit arithmetic and the CountDown task show a problem-specific "sweet spot." Past it, extra reasoning harms performance. The authors also test token-budget following and RL training with a modified reward.
- **Context handling:** R1 readily lets context override its parametric knowledge. With very long inputs (e.g., needle-in-a-haystack), it can become overwhelmed and produce incoherent text.
- **Safety and culture:** On HarmBench, R1 is more vulnerable than DeepSeek-V3, and its outputs work as jailbreaks against Gemma2 and Llama-3.1. Moral and cultural probes (Defining Issues Test, LLM-GLOBE) show longer reasoning and different values in English than in Chinese.
- **Cognition and release:** R1 writes longer chains for garden-path sentences and comparative illusions, but behaves unlike humans on simple control sentences. In ASCII drawing and physics simulation tasks, it identifies the parts but fails to integrate them. Code and model outputs are available at github.com/McGill-NLP/thoughtology.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 4,145 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,948 works

## Cite

Cite as: Sara Vera Marjanovic, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing Han Lu, Nicholas Meade, Dongchan Shin, Amirhossein Kazemnejad, Gaurav Kamath, Marius Mosbach, Karolina Stanczak and Siva Reddy. 2025. DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning. arXiv:2504.07128.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{marjanovic2025deepseek,
  title = {{DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning}},
  author = {Sara Vera Marjanovic, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing Han Lu, Nicholas Meade, Dongchan Shin, Amirhossein Kazemnejad, Gaurav Kamath, Marius Mosbach, Karolina Stanczak and Siva Reddy},
  year = {2025},
  doi = {10.48550/arxiv.2504.07128},
  eprint = {2504.07128},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2504.07128}
}
```

- [← previous Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://md.research.elamur.ai/free/en/papers/zhang-2025-darwin-godel-machine-open/)
- [next → Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models](https://md.research.elamur.ai/free/en/papers/wu-2025-rethinking-kullback-leibler-divergence-knowledge/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

143 references, 62 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mostafa Abdou, Artur Kulmizev, Daniel Hershcovich, Stella Frank, Ellie Pavlick, and Anders Søgaard. [Can language models encode perceptual structure without grounding? A case study in color](https://md.research.elamur.ai/free/en/papers/abdou-2021-can-language-models-encode-perceptual/). In Proceedings of the 25th Conference on Computational Natural Language Learning, pp. 109–132, 2021. URL https…
2. Rakefet Ackerman and Valerie A. Thompson. Meta-reasoning: Monitoring and control of thinking and reasoning. Trends in Cognitive Sciences, 21(8):607–617, 2017. ISSN 1364-6613. doi: https://doi.org/10.1016/ j.tics.2017.05.004. URL https://www.sciencedirect.com/science/article/pii/S1364661317301055. [find](https://scholar.google.com/scholar?q=Rakefet+Ackerman+and+Valerie+A%2E+Thompson%2E+Meta%2Dreasoning%3A+Monitoring+and+control+of+thinking+and+reasoning%2E+Trends+in+Cognitive+Sciences%2C+21%288%29%3A607%E2%80%93617%2C+2017%2E+ISSN+1364%2D6613%2E+doi%3A+https%3A%2F%2Fdoi%2Eorg%2F10%2E1)
3. Vaibhav Adlakha, Parishad BehnamGhader, Xing Han Lu, Nicholas Meade, and Siva Reddy. [Evaluating correctness and faithfulness of instruction-following models for question answering](https://md.research.elamur.ai/free/en/papers/adlakha-2024-evaluating-correctness-faithfulness-instruction-following/). Transactions of the Association for Computational Linguistics, 12:681–699, 2024. doi: 10.1162/tacl_a_00667. URL https:…
4. Pranjal Aggarwal and Sean Welleck. [L1: Controlling how long a reasoning model thinks with reinforcement learning](https://md.research.elamur.ai/free/en/papers/aggarwal-2025-l1-controlling-long-reasoning-model/), 2025. URL https://arxiv.org/abs/2503.04697. [↗](https://arxiv.org/abs/2503.04697)
5. Samuel Joseph Amouyal, Aya Meltzer-Asscher, and Jonathan Berant. When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models, February 2025. URL http://arxiv.org/abs/2502.09307. arXiv:2502.09307 [cs]. [↗](http://arxiv.org/abs/2502.09307)
6. Jacob Andreas, 2024. URL "https://lingo.csail.mit.edu/blog/world_models/". [find](https://scholar.google.com/scholar?q=Jacob+Andreas%2C+2024%2E+URL+%22https%3A%2F%2Flingo%2Ecsail%2Emit%2Eedu%2Fblog%2Fworld%5Fmodels%2F%22%2E)
7. Anthropic. Claude 3.7 sonnet system card, 2025a. URL [https://assets.anthropic.com/m/](https://assets.anthropic.com/m/) 785e231869ea8b3b/original/claude-3-7-sonnet-system-card.pdf. [↗](https://assets.anthropic.com/m/)
8. Anthropic. Tracing the thoughts of a large language model, 2025b. URL [https://www.anthropic.com/](https://www.anthropic.com/) research/tracing-thoughts-language-model. [↗](https://www.anthropic.com/)
9. Suhas Arehalli, Brian Dillon, and Tal Linzen. Syntactic surprisal from neural models predicts, but underestimates, human processing difficulty from syntactic ambiguities. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pp. 301–313, Abu Dhabi, United Arab Emi… [find](https://scholar.google.com/scholar?q=Suhas+Arehalli%2C+Brian+Dillon%2C+and+Tal+Linzen%2E+Syntactic+surprisal+from+neural+models+predicts%2C+but+underestimates%2C+human+processing+difficulty+from+syntactic+ambiguities%2E+In+Proceedings+of+the+26th+Co)
10. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Sh… [find](https://scholar.google.com/scholar?q=Yuntao+Bai%2C+Andy+Jones%2C+Kamal+Ndousse%2C+Amanda+Askell%2C+Anna+Chen%2C+Nova+DasSarma%2C+Dawn+Drain%2C+Stanislav+Fort%2C+Deep+Ganguli%2C+Tom+Henighan%2C+Nicholas+Joseph%2C+Saurav+Kadavath%2C+Jackson+Kernion%2C+Tom+Conerly%2C+)
11. Andreas Blattmann, Tim Dockhorn, Sumith Kulal, Daniel Mendelevitch, Maciej Kilian, Dominik Lorenz, Yam Levi, Zion English, Vikram Voleti, Adam Letts, et al. Stable video diffusion: Scaling latent video diffusion models to large datasets. CoRR, 2023. [find](https://scholar.google.com/scholar?q=Andreas+Blattmann%2C+Tim+Dockhorn%2C+Sumith+Kulal%2C+Daniel+Mendelevitch%2C+Maciej+Kilian%2C+Dominik+Lorenz%2C+Yam+Levi%2C+Zion+English%2C+Vikram+Voleti%2C+Adam+Letts%2C+et+al%2E+Stable+video+diffusion%3A+Scaling+latent+vide)
12. Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. Language (technology) is power: A critical survey of “bias” in NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5454[–5476, 2020](https://md.research.elamur.ai/free/en/papers/blodgett-2020-language-technology-is-power-critical/).
13. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
14. Jake Bruce, Michael D Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, et al. GENIE: Generative interactive environments. In Forty-first International Conference on Machine Learning, 2024. [find](https://scholar.google.com/scholar?q=Jake+Bruce%2C+Michael+D+Dennis%2C+Ashley+Edwards%2C+Jack+Parker%2DHolder%2C+Yuge+Shi%2C+Edward+Hughes%2C+Matthew+Lai%2C+Aditi+Mavalankar%2C+Richie+Steigerwald%2C+Chris+Apps%2C+et+al%2E+GENIE%3A+Generative+interactive+environme)
15. Maarten Buyl, Alexander Rogiers, Sander Noels, Guillaume Bied, Iris Dominguez-Catena, Edith Heiter, Iman Johary, Alexandru-Cristian Mara, Raphaël Romero, Jefrey Lijffijt, and Tijl De Bie. Large language models reflect the ideology of their creators, 2025. URL https://arxiv.org/abs/2410.18417. — [arXiv:2410.18417](https://arxiv.org/abs/2410.18417) [↗](https://arxiv.org/abs/2410.18417)
16. Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong. [Jailbreakbench: An open robustness benchmark for jailbreaking large language models](https://md.research.elamur.ai/free/en/papers/chao-2024-jailbreakbench-open-robustness-benchmark-jailbreaking/). In The T…
17. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168, 2021. URL [https://arxiv.org/](https://arxiv.org/) a… [↗](https://arxiv.org/)
18. T.H. Cormen, C.E. Leiserson, R.L. Rivest, and C. Stein. Introduction to Algorithms, fourth edition. MIT Press, 2022. ISBN 9780262367509. URL [https://books.google.ca/books?id=RSMuEAAAQBAJ](https://books.google.ca/books?id=RSMuEAAAQBAJ). [↗](https://books.google.ca/books?id=RSMuEAAAQBAJ)
19. Carlos G. Correa, Mark K. Ho, Frederick Callaway, Nathaniel D. Daw, and Thomas L. Griffiths. Humans decompose tasks by trading off utility and computational cost. PLOS Computational Biology, 19(6): e1011087, June 2023. ISSN 1553-7358. doi: 10.1371/journal.pcbi.1011087. URL http://dx.doi.org/10. 1371… — [doi:10.1371/journal.pcbi.1011087](https://doi.org/10.1371/journal.pcbi.1011087) [find](https://scholar.google.com/scholar?q=Carlos+G%2E+Correa%2C+Mark+K%2E+Ho%2C+Frederick+Callaway%2C+Nathaniel+D%2E+Daw%2C+and+Thomas+L%2E+Griffiths%2E+Humans+decompose+tasks+by+trading+off+utility+and+computational+cost%2E+PLOS+Computational+Biology%2C+19%286%29%3A+e1)
20. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chengg… — [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/)
21. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, H… [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+Damai+Dai%2C+Daya+Guo%2C+Dejian+Yang%2C+Deli+Chen%2C+Dongjie+Ji%2C+Erhan)
22. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volum…
23. Alexandros Dimakis. [twitter post]. Twitter, 2025. URL [https://x.com/AlexGDimakis/status/](https://x.com/AlexGDimakis/status/) 1885447830120362099. Retrieved from https://x.com/AlexGDimakis/status/1885447830120362099. [↗](https://x.com/AlexGDimakis/status/)
24. Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, Edoardo M. Ponti, and Siva Reddy. [FaithDial: A faithful benchmark for information-seeking dialogue](https://md.research.elamur.ai/free/en/papers/dziri-2022-faithdial-faithful-benchmark-information-seeking/). Transactions of the Association for Computational Linguistics, 10:1473–1490, 2022. doi: 10.1162/tacl_a_00529. URL [https://aclanthology.…](https://aclanthology.…) [↗](https://aclanthology.…)
25. Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Sean Welleck, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, and Yejin Choi. [Faith and fate: Limits of transformers on compositionality](https://md.research.elamur.ai/free/en/papers/dziri-2023-faith-fate-limits-transformers-compositionality/).…
26. Fernanda Ferreira, Kiel Christianson, and Andrew Hollingworth. Misinterpretations of garden-path sentences: Implications for models of sentence processing and reanalysis. Journal of Psycholinguistic Research, 30(1):3–20, 2001. ISSN 00906905. doi: 10.1023/A:1005290706460. — [doi:10.1023/a:1005290706460](https://doi.org/10.1023/a:1005290706460) [find](https://scholar.google.com/scholar?q=Fernanda+Ferreira%2C+Kiel+Christianson%2C+and+Andrew+Hollingworth%2E+Misinterpretations+of+garden%2Dpath+sentences%3A+Implications+for+models+of+sentence+processing+and+reanalysis%2E+Journal+of+Psycholinguistic+R)
27. Fernanda Ferreira, Karl G.D. Bailey, and Vittoria Ferraro. Good-enough representations in language comprehension. Current Directions in Psychological Science, 11(1):11–15, 2002. doi: 10.1111/1467-8721.00158. URL https://doi.org/10.1111/1467-8721.00158. — [doi:10.1111/1467-8721.00158](https://doi.org/10.1111/1467-8721.00158) [↗](https://doi.org/10.1111/1467-8721.00158)
28. Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. [Complexity-based prompting for multi-step reasoning](https://md.research.elamur.ai/free/en/papers/fu-2022-complexity-based-prompting-multi-step/). In The Eleventh International Conference on Learning Representations, 2023. URL [https://openreview.net/forum?id=yf1icZHC-l9](https://openreview.net/forum?id=yf1icZHC-l9). [↗](https://openreview.net/forum?id=yf1icZHC-l9)
29. Kanishk Gandhi, Denise H J Lee, Gabriel Grand, Muxin Liu, Winson Cheng, Archit Sharma, and Noah Goodman. [Stream of search (sos): Learning to search in language](https://md.research.elamur.ai/free/en/papers/gandhi-2024-stream-search-sos-learning-search/). In First Conference on Language Modeling, 2024. URL [https://openreview.net/forum?id=2cop2jmQVL](https://openreview.net/forum?id=2cop2jmQVL). [↗](https://openreview.net/forum?id=2cop2jmQVL)
30. Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, and Noah D. Goodman. [Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars](https://md.research.elamur.ai/free/en/papers/gandhi-2025-cognitive-behaviors-that-enable-self/), 2025. URL https://arxiv.org/abs/2503.01307. [↗](https://arxiv.org/abs/2503.01307)
31. Yunfan Gao, Yun Xiong, Wenlong Wu, Zijing Huang, Bohan Li, and Haofen Wang. U-NIAH: Unified RAG and LLM evaluation for long context needle-in-a-haystack, 2025. URL https://arxiv.org/abs/2503. 00353. [↗](https://arxiv.org/abs/2503)
32. Gemini Team et al. [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/), 2024. URL https://arxiv.org/abs/2403.05530. [↗](https://arxiv.org/abs/2403.05530)
33. Dedre Gentner and Albert L Stevens. Mental models. Psychology Press, 2014. [find](https://scholar.google.com/scholar?q=Dedre+Gentner+and+Albert+L+Stevens%2E+Mental+models%2E+Psychology+Press%2C+2014%2E)
34. Google. Gemini 2.5: Our most intelligent ai model, 2025. URL [https://blog.google/](https://blog.google/) technology/google-deepmind/gemini-model-thinking-updates-march-2025/?_bhlid= e5b81688cdae64f414e4acb57a31fc46e19c83a7\#gemini-2-5-thinking. [↗](https://blog.google/)
35. Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, and Yinfei Yang. [LongT5: Efficient text-to-text transformer for long sequences](https://md.research.elamur.ai/free/en/papers/guo-2022-longt5-efficient-text-text-transformer/). In Marine Carpuat, Marie-Catherine de Marneffe, and Ivan Vladimir Meza Ruiz (eds.), Findings of the Association for Computational Lingu…
36. Wes Gurnee and Max Tegmark. Language models represent space and time. In The Twelfth International Conference on Learning Representations, 2024. [find](https://scholar.google.com/scholar?q=Wes+Gurnee+and+Max+Tegmark%2E+Language+models+represent+space+and+time%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2C+2024%2E)
37. Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian. Training large language models to reason in a continuous latent space, 2024. URL [https://arxiv.org/](https://arxiv.org/) abs/2412.06769. [↗](https://arxiv.org/)
38. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). NeurIPS, 2021.
39. Mark K. Ho, David Abel, Carlos G. Correa, Michael L. Littman, Jonathan D. Cohen, and Thomas L. Griffiths. People construct simplified mental representations to plan. Nature, 606(7912):129–136, May 2022. ISSN 1476-4687. doi: 10.1038/s41586-022-04743-9. URL http://dx.doi.org/10.1038/ s41586-022-04743-… — [doi:10.1038/s41586-022-04743-9](https://doi.org/10.1038/s41586-022-04743-9) [find](https://scholar.google.com/scholar?q=Mark+K%2E+Ho%2C+David+Abel%2C+Carlos+G%2E+Correa%2C+Michael+L%2E+Littman%2C+Jonathan+D%2E+Cohen%2C+and+Thomas+L%2E+Griffiths%2E+People+construct+simplified+mental+representations+to+plan%2E+Nature%2C+606%287912%29%3A129%E2%80%93136%2C+May+202)
40. Nick Huang and Colin Phillips. When missing NPs make double center-embedding sentences acceptable. Glossa: a journal of general linguistics, 6(1), April 2021. ISSN 2397-1835. doi: 10.5334/gjgl.1292. URL [https://www.glossa-journal.org/article/id/5417/](https://www.glossa-journal.org/article/id/5417/). [↗](https://www.glossa-journal.org/article/id/5417/)
41. Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, and Madian Khabsa. [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://md.research.elamur.ai/free/en/papers/inan-2023-llama-guard-llm-based-input/), December 2023. URL http://arxiv.org/abs/2312.06674. arXiv:231… [↗](http://arxiv.org/abs/2312.06674)
42. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. [SWE-bench: Can language models resolve real-world GitHub issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) In The Twelfth International Conference on Learning Representations, 2024. URL [https://openreview.net/forum?id=](https://openreview.net/forum?id=) VTF8yNQM66. [↗](https://openreview.net/forum?id=)
43. Philip N Johnson-Laird. Mental models in cognitive science. Cognitive science, 4(1):71–115, 1980. [find](https://scholar.google.com/scholar?q=Philip+N+Johnson%2DLaird%2E+Mental+models+in+cognitive+science%2E+Cognitive+science%2C+4%281%29%3A71%E2%80%93115%2C+1980%2E)
44. Daniel Kahneman. Thinking, fast and slow. Macmillan, 2011. [find](https://scholar.google.com/scholar?q=Daniel+Kahneman%2E+Thinking%2C+fast+and+slow%2E+Macmillan%2C+2011%2E)
45. Greg Kamradt. Needle in a haystack - pressure testing LLMs. [https://github.com/gkamradt/LLMTest_](https://github.com/gkamradt/LLMTest_) NeedleInAHaystack, 2023. [↗](https://github.com/gkamradt/LLMTest_)
46. Elise Karinshak, Amanda Hu, Kewen Kong, Vishwanatha Rao, Jingren Wang, Jindong Wang, and Yi Zeng. Llm-globe: A benchmark evaluating the cultural values embedded in LLM output, 2024. URL https://arxiv.org/abs/2411.06032. — [arXiv:2411.06032](https://arxiv.org/abs/2411.06032) [↗](https://arxiv.org/abs/2411.06032)
47. Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, and Deepak Ramachandran. [LAMBADA: Backward chaining for automated reasoning in natural language](https://md.research.elamur.ai/free/en/papers/kazemi-2023-lambada-backward-chaining-automated-reasoning/). In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (…
48. Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron Courville, and Nicolas Le Roux. VinePPO: Unlocking RL potential for LLM reasoning through refined credit assignment, 2024. [URL https://arxiv.org/abs/2410.01679](https://md.research.elamur.ai/free/en/papers/kazemnejad-2024-vineppo-refining-credit-assignment-rl/). [↗](https://arxiv.org/abs/2410.01679)
49. Aditi Khandelwal, Utkarsh Agarwal, Kumar Tanmay, and Monojit Choudhury. Do moral judgment and reasoning capability of llms change with language? a study using the multilingual defining issues test. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Aditi+Khandelwal%2C+Utkarsh+Agarwal%2C+Kumar+Tanmay%2C+and+Monojit+Choudhury%2E+Do+moral+judgment+and+reasoning+capability+of+llms+change+with+language%3F+a+study+using+the+multilingual+defining+issues+test%2E+In)
50. Yekyung Kim, Jenna Russell, Marzena Karpinska, and Mohit Iyyer. One ruler to measure them all: Benchmarking multilingual long-context language models, 2025. URL https://arxiv.org/abs/2503.01996. — [arXiv:2503.01996](https://arxiv.org/abs/2503.01996) [↗](https://arxiv.org/abs/2503.01996)
51. Günther Knoblich, Stellan Ohlsson, Hilde Haider, and Detlef Rhenius. Constraint relaxation and chunk decomposition in insight problem solving. Journal of Experimental Psychology: Learning, Memory, and Cognition, 25:1534–1555, 11 1999. doi: 10.1037/0278-7393.25.6.1534. [find](https://scholar.google.com/scholar?q=G%C3%BCnther+Knoblich%2C+Stellan+Ohlsson%2C+Hilde+Haider%2C+and+Detlef+Rhenius%2E+Constraint+relaxation+and+chunk+decomposition+in+insight+problem+solving%2E+Journal+of+Experimental+Psychology%3A+Learning%2C+Memory%2C+and)
52. Mike Knoop. R1-zero and r1 results and analysis. ARC Prize Blog, January 2025. URL [https://arcprize.org/blog/r1-zero-r1-results-analysis](https://arcprize.org/blog/r1-zero-r1-results-analysis). [↗](https://arcprize.org/blog/r1-zero-r1-results-analysis)
53. Lawrence Kohlberg and Richard H Hersh. Moral development: A review of the theory. Theory into practice, 16(2):53–59, 1977. [find](https://scholar.google.com/scholar?q=Lawrence+Kohlberg+and+Richard+H+Hersh%2E+Moral+development%3A+A+review+of+the+theory%2E+Theory+into+practice%2C+16%282%29%3A53%E2%80%9359%2C+1977%2E)
54. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (eds.), Advances in Neural Information Processing Systems, 2022. URL [https://openreview.net/forum?](https://openreview.net/forum?) id=… [↗](https://openreview.net/forum?)
55. Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal Behbahani, and Aleksandra Faust. Training language models to… — [Training Language Models to Self-Correct via Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/kumar-2024-training-language-models-self-correct/)
56. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. [Natural Questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Linguistics, 7:4…
57. Nathan Lambert. Reinforcement Learning from Human Feedback. Online, 2024. URL [https://rlhfbook.com](https://rlhfbook.com). [↗](https://rlhfbook.com)
58. Jason Lee, Kyunghyun Cho, and Douwe Kiela. Countering language drift via visual grounding. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan (eds.), Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lan… [find](https://scholar.google.com/scholar?q=Jason+Lee%2C+Kyunghyun+Cho%2C+and+Douwe+Kiela%2E+Countering+language+drift+via+visual+grounding%2E+In+Kentaro+Inui%2C+Jing+Jiang%2C+Vincent+Ng%2C+and+Xiaojun+Wan+%28eds%2E%29%2C+Proceedings+of+the+2019+Conference+on+Empiri)
59. Roger Levy. Expectation-based syntactic comprehension. Cognition, 106(3):1126–1177, 2008. ISSN 0010-0277. doi: https://doi.org/10.1016/j.cognition.2007.05.006. URL https://www.sciencedirect.com/ science/article/pii/S0010027707001436. — [doi:10.1016/j.cognition.2007.05.006](https://doi.org/10.1016/j.cognition.2007.05.006) [↗](https://doi.org/10.1016/j.cognition.2007.05.006)
60. Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. [Making language models better reasoners with step-aware verifier](https://md.research.elamur.ai/free/en/papers/li-2023-making-language-models-better-reasoners/). In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguis…
61. Yuannan Li, Shan Xu, and Jia Liu. The neural correlates of logical-mathematical symbol systems processing resemble those of spatial cognition more than language processing. iScience, 28(4), 2025a. [find](https://scholar.google.com/scholar?q=Yuannan+Li%2C+Shan+Xu%2C+and+Jia+Liu%2E+The+neural+correlates+of+logical%2Dmathematical+symbol+systems+processing+resemble+those+of+spatial+cognition+more+than+language+processing%2E+iScience%2C+28%284%29%2C+2025a%2E)
62. Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhijiang Guo, Le Song, and Cheng-Lin Liu. [From System 1 to System 2: A survey of reasoning large language models](https://md.research.elamur.ai/free/en/papers/li-2025-system-1-system-2-survey/), 2025b. URL…
63. Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step, 2023. URL — [Let's Verify Step by Step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/) [https://arxiv.org/](https://arxiv.org/) abs/2305.20050. [↗](https://arxiv.org/)
64. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. [RoBERTa: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692, 2019.
65. Llama Team et al. [The Llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/), 2024. arXiv:2407.21783.
66. URL https://arxiv.org/abs/2407.21783. MAA. American invitational mathematics examination - AIME. In American Invitational Mathematics Examination - AIME 2024, February 2024. URL https://maa.org/math-competitions/ american-invitational-mathematics-examination-aime. — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/) [↗](https://arxiv.org/abs/2407.21783)
67. James Macgregor, Thomas Ormerod, and Edward Chronicle. Information processing and insight: A process model of performance on the nine-dot and related problems. Journal of experimental psychology. Learning, memory, and cognition, 27:176–201, 02 2001. doi: 10.1037//0278-7393.27.1.176. — [doi:10.1037//0278-7393.27.1.176](https://doi.org/10.1037//0278-7393.27.1.176) [find](https://scholar.google.com/scholar?q=James+Macgregor%2C+Thomas+Ormerod%2C+and+Edward+Chronicle%2E+Information+processing+and+insight%3A+A+process+model+of+performance+on+the+nine%2Ddot+and+related+problems%2E+Journal+of+experimental+psychology%2E+Lear)
68. Andreas Madsen, Sarath Chandar, and Siva Reddy. Are self-explanations from large language models faithful? In Lun-Wei Ku, Andre Martins, and Vivek Srikumar (eds.), Findings of the Association for Computational Linguistics: ACL 2024, pp. 295–337, Bangkok, Thailand, August 2024. Association for Comput… [find](https://scholar.google.com/scholar?q=Andreas+Madsen%2C+Sarath+Chandar%2C+and+Siva+Reddy%2E+Are+self%2Dexplanations+from+large+language+models+faithful%3F+In+Lun%2DWei+Ku%2C+Andre+Martins%2C+and+Vivek+Srikumar+%28eds%2E%29%2C+Findings+of+the+Association+for+Comp)
69. Seiji Maekawa, Hayate Iso, and Nikita Bhutani. Holistic reasoning with long-context LMs: A benchmark for database operations on massive textual data. In The Thirteenth International Conference on Learning Representations, 2025. URL [https://openreview.net/forum?id=5LXcoDtNyq](https://openreview.net/forum?id=5LXcoDtNyq). [↗](https://openreview.net/forum?id=5LXcoDtNyq)
70. Kyle Mahowald, Anna A Ivanova, Idan A Blank, Nancy Kanwisher, Joshua B Tenenbaum, and Evelina Fedorenko. Dissociating language and thought in large language models. Trends in cognitive sciences, 28 (6):517–540, 2024. [find](https://scholar.google.com/scholar?q=Kyle+Mahowald%2C+Anna+A+Ivanova%2C+Idan+A+Blank%2C+Nancy+Kanwisher%2C+Joshua+B+Tenenbaum%2C+and+Evelina+Fedorenko%2E+Dissociating+language+and+thought+in+large+language+models%2E+Trends+in+cognitive+sciences%2C+28+%286)
71. Sara Vera Marjanovic, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, and Isabelle Augenstein. DYNAMICQA: Tracing internal knowledge conflicts in language models. In Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (eds.), Findings of the Association for Computational Linguistics: EMNLP 2… [find](https://scholar.google.com/scholar?q=Sara+Vera+Marjanovic%2C+Haeun+Yu%2C+Pepa+Atanasova%2C+Maria+Maistro%2C+Christina+Lioma%2C+and+Isabelle+Augenstein%2E+DYNAMICQA%3A+Tracing+internal+knowledge+conflicts+in+language+models%2E+In+Yaser+Al%2DOnaizan%2C+Mohit+)
72. Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, and Dan Hendrycks. [HarmBench: a standardized evaluation framework for automated red teaming and robust refusal](https://md.research.elamur.ai/free/en/papers/mazeika-2024-harmbench-standardized-evaluation-framework-automated/). In Proceedings of the 41st International Conferenc…
73. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. [Rethinking the role of demonstrations: What makes in-context learning work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/) In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (eds.), Proceedings of the 2022 Conference on Empirical Methods in…
74. Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen, Caiming Xiong, and Shafiq Joty. FaithEval: Can your language model stay faithful to context, even if “the moon is made of marshmallows”. In The Thirteenth International Conference on Learning Representations, 2025. URL https… [find](https://scholar.google.com/scholar?q=Yifei+Ming%2C+Senthil+Purushwalkam%2C+Shrey+Pandit%2C+Zixuan+Ke%2C+Xuan%2DPhi+Nguyen%2C+Caiming+Xiong%2C+and+Shafiq+Joty%2E+FaithEval%3A+Can+your+language+model+stay+faithful+to+context%2C+even+if+%E2%80%9Cthe+moon+is+made+of+ma)
75. Melanie Mitchell. [bluesky post]. Bluesky, 2025. profile/melaniemitchell.bsky.social/post/3ljqgfiopx22f. [https://bsky.app/profile/melaniemitchell.bsky.social/post/3ljqgfiopx22f](https://bsky.app/profile/melaniemitchell.bsky.social/post/3ljqgfiopx22f). [↗](https://bsky.app/profile/melaniemitchell.bsky.social/post/3ljqgfiopx22f)
76. URL — [s1: Simple test-time scaling](https://md.research.elamur.ai/free/en/papers/muennighoff-2025-s1-simple-test-time-scaling/) [https://bsky.app/](https://bsky.app/) Retrieved from Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. s1: Simple test-time scaling, 2025. URL https://arxiv.org/abs/2501.19393. [↗](https://bsky.app/)
77. Milad Nasr, Javier Rando, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Florian Tramèr, and Katherine Lee. Scalable Extraction of Training Data from Aligned, Production Language Models. In The Thirteenth International Conferenc… [find](https://scholar.google.com/scholar?q=Milad+Nasr%2C+Javier+Rando%2C+Nicholas+Carlini%2C+Jonathan+Hayase%2C+Matthew+Jagielski%2C+A%2E+Feder+Cooper%2C+Daphne+Ippolito%2C+Christopher+A%2E+Choquette%2DChoo%2C+Florian+Tram%C3%A8r%2C+and+Katherine+Lee%2E+Scalable+Extraction+)
78. Haomiao Ni, Changhao Shi, Kai Li, Sharon X Huang, and Martin Renqiang Min. Conditional image-to-video generation with latent flow diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 18444–18455, 2023. [find](https://scholar.google.com/scholar?q=Haomiao+Ni%2C+Changhao+Shi%2C+Kai+Li%2C+Sharon+X+Huang%2C+and+Martin+Renqiang+Min%2E+Conditional+image%2Dto%2Dvideo+generation+with+latent+flow+diffusion+models%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+compute)
79. Michael Noukhovitch, Samuel Lavoie, Florian Strub, and Aaron Courville. Language model alignment with elastic reset. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. URL [https://openreview.net/forum?id=6lgugutkin](https://openreview.net/forum?id=6lgugutkin). [↗](https://openreview.net/forum?id=6lgugutkin)
80. Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, and Aaron Courville. Asynchronous rlhf: Faster and more efficient off-policy rl for language models, 2025. URL https://arxiv.org/abs/2410.18252. — [arXiv:2410.18252](https://arxiv.org/abs/2410.18252) [↗](https://arxiv.org/abs/2410.18252)
81. Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, Charles Sutton, and Augustus Odena. [Show your work: Scratchpads for intermediate computation with language models](https://md.research.elamur.ai/free/en/papers/al-2021-show-your-work-scratchpads-intermediate/). In Deep Learning for Code Wor…
82. Ellen O’Connor. Comparative iIlusions at the syntax-semantics interface. PhD dissertation, University of Southern California, Los Angeles, CA, 2015. [find](https://scholar.google.com/scholar?q=Ellen+O%E2%80%99Connor%2E+Comparative+iIlusions+at+the+syntax%2Dsemantics+interface%2E+PhD+dissertation%2C+University+of+Southern+California%2C+Los+Angeles%2C+CA%2C+2015%2E)
83. OpenAI. Learning to reason learning-to-reason-with-llms/. with LLMs, 2024. [find](https://scholar.google.com/scholar?q=OpenAI%2E+Learning+to+reason+learning%2Dto%2Dreason%2Dwith%2Dllms%2F%2E+with+LLMs%2C+2024%2E)
84. URL — [gpt-oss-120b & gpt-oss-20b Model Card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/) [https://openai.com/index/OpenAI](https://openai.com/index/OpenAI), :, Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, Kai Chen, Mark… [↗](https://openai.com/index/OpenAI)
85. OpenAI Team et al. arXiv:2303.08774. [GPT-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/), 2024.
86. URL https://arxiv.org/abs/2303.08774. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Gray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano… — [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/) [↗](https://arxiv.org/abs/2303.08774)
87. Jiayi Pan, Junjie Zhang, Xingyao Wang, Lifan Yuan, Hao Peng, and Alane Suhr. [https://github.com/Jiayi-Pan/TinyZero](https://github.com/Jiayi-Pan/TinyZero), 2025. Accessed: 2025-01-24. [↗](https://github.com/Jiayi-Pan/TinyZero)
88. TinyZero. Richard Yuanzhe Pang, Weizhe Yuan, He He, Kyunghyun Cho, Sainbayar Sukhbaatar, and Jason E Weston. [Iterative reasoning preference optimization](https://md.research.elamur.ai/free/en/papers/pang-2024-iterative-reasoning-preference-optimization/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024. URL [https://openreview.net/forum?id=4XIKfvNYvx](https://openreview.net/forum?id=4XIKfvNYvx). [↗](https://openreview.net/forum?id=4XIKfvNYvx)
89. Letitia Parcalabescu and Anette Frank. On Measuring Faithfulness or Self-consistency of Natural Language Explanations. In Lun-Wei Ku, Andre Martins, and Vivek Srikumar (eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6048–60… [find](https://scholar.google.com/scholar?q=Letitia+Parcalabescu+and+Anette+Frank%2E+On+Measuring+Faithfulness+or+Self%2Dconsistency+of+Natural+Language+Explanations%2E+In+Lun%2DWei+Ku%2C+Andre+Martins%2C+and+Vivek+Srikumar+%28eds%2E%29%2C+Proceedings+of+the+62nd+)
90. Arkil Patel, Siva Reddy, and Dzmitry Bahdanau. How to get your LLM to generate challenging problems for evaluation, 2025. URL https://arxiv.org/abs/2502.14678. [↗](https://arxiv.org/abs/2502.14678)
91. Ethan Perez, Patrick Lewis, Wen-tau Yih, Kyunghyun Cho, and Douwe Kiela. [Unsupervised question decomposition for question answering](https://md.research.elamur.ai/free/en/papers/perez-2020-unsupervised-question-decomposition-question-answering/). In Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu (eds.), Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8864–…
92. George Polya. Mathematics and Plausible Reasoning, Volume 1. Princeton University Press, Princeton, 1954. ISBN 9780691218304. doi: doi:10.1515/9780691218304. URL https://doi.org/10.1515/ 9780691218304. [find](https://scholar.google.com/scholar?q=George+Polya%2E+Mathematics+and+Plausible+Reasoning%2C+Volume+1%2E+Princeton+University+Press%2C+Princeton%2C+1954%2E+ISBN+9780691218304%2E+doi%3A+doi%3A10%2E1515%2F9780691218304%2E+URL+https%3A%2F%2Fdoi%2Eorg%2F10%2E1515%2F+9780691218304)
93. Sufyani Prabawanto. Students’ validations on their solution in mathematical problem solving. Journal of Physics: Conference Series, 1157:042111, 02 2019. doi: 10.1088/1742-6596/1157/4/042111. — [doi:10.1088/1742-6596/1157/4/042111](https://doi.org/10.1088/1742-6596/1157/4/042111) [find](https://scholar.google.com/scholar?q=Sufyani+Prabawanto%2E+Students%E2%80%99+validations+on+their+solution+in+mathematical+problem+solving%2E+Journal+of+Physics%3A+Conference+Series%2C+1157%3A042111%2C+02+2019%2E+doi%3A+10%2E1088%2F1742%2D6596%2F1157%2F4%2F042111%2E+%E2%80%94+%5Bdoi%3A1)
94. Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, and Aviral Kumar. Optimizing test-time compute via meta reinforcement fine-tuning, 2025. URL https://arxiv.org/abs/2503.07572. [↗](https://arxiv.org/abs/2503.07572)
95. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2C+2019%2E)
96. Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, and Richard Socher. [Explain yourself! Leveraging language models for commonsense reasoning](https://md.research.elamur.ai/free/en/papers/rajani-2019-explain-yourself-leveraging-language-models/). In Anna Korhonen, David Traum, and Lluís Màrquez (eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4932–4…
97. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. [Hierarchical text-conditional image generation with clip latents](https://md.research.elamur.ai/free/en/papers/ramesh-2022-hierarchical-text-conditional-image-generation/). arXiv preprint arXiv:2204.06125, 2022.
98. Abhinav Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, and Monojit Choudhury. Ethical reasoning over moral alignment: A case and framework for in-context ethical policies in llms. In Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 13370–13388, 2023. [find](https://scholar.google.com/scholar?q=Abhinav+Rao%2C+Aditi+Khandelwal%2C+Kumar+Tanmay%2C+Utkarsh+Agarwal%2C+and+Monojit+Choudhury%2E+Ethical+reasoning+over+moral+alignment%3A+A+case+and+framework+for+in%2Dcontext+ethical+policies+in+llms%2E+In+Findings+o)
99. J R Rest. DIT manual : manual for the defining issues test. University of Minnesota Press, Minneapolis, MN, 1986. [find](https://scholar.google.com/scholar?q=J+R+Rest%2E+DIT+manual+%3A+manual+for+the+defining+issues+test%2E+University+of+Minnesota+Press%2C+Minneapolis%2C+MN%2C+1986%2E)
100. Alexander Rush and Daniel Ritter. O1 tutorial, 2025. URL [https://srush.github.io/awesome-o1/](https://srush.github.io/awesome-o1/) o1-tutorial.pdf. [↗](https://srush.github.io/awesome-o1/)
101. Swarnadeep Saha, Archiki Prasad, Justin Chen, Peter Hase, Elias Stengel-Eskin, and Mohit Bansal. System 1.x: Learning to balance fast and slow planning with language models. In The Thirteenth International Conference on Learning Representations, 2025. URL [https://openreview.net/forum?id=zd0iX5xBhA](https://openreview.net/forum?id=zd0iX5xBhA). [↗](https://openreview.net/forum?id=zd0iX5xBhA)
102. Abulhair Saparov and He He. [Language models are greedy reasoners: A systematic formal analysis of chain-of-thought](https://md.research.elamur.ai/free/en/papers/saparov-2022-language-models-greedy-reasoners-systematic/). In The Eleventh International Conference on Learning Representations, 2023. URL [https://openreview.net/forum?id=qFVVBzXxR2V](https://openreview.net/forum?id=qFVVBzXxR2V). [↗](https://openreview.net/forum?id=qFVVBzXxR2V)
103. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms, 2017. URL https://arxiv.org/abs/1707.06347. [↗](https://arxiv.org/abs/1707.06347)
104. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. [DeepSeekMath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/), 2024. URL https://arxiv.org/abs/2402.03300. [↗](https://arxiv.org/abs/2402.03300)
105. David Silver, Aja Huang, Christopher J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray… [find](https://scholar.google.com/scholar?q=David+Silver%2C+Aja+Huang%2C+Christopher+J%2E+Maddison%2C+Arthur+Guez%2C+Laurent+Sifre%2C+George+van+den+Driessche%2C+Julian+Schrittwieser%2C+Ioannis+Antonoglou%2C+Veda+Panneershelvam%2C+Marc+Lanctot%2C+Sander+Dieleman%2C+Do)
106. Avi Singh, John D Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Xavier Garcia, Peter J Liu, James Harrison, Jaehoon Lee, Kelvin Xu, Aaron T Parisi, Abhishek Kumar, Alexander A Alemi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, Gamaleldin Fathy Elsayed, Hanie Sedghi, Igor Mordatch,… — [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://md.research.elamur.ai/free/en/papers/singh-2023-human-data-scaling-self-training/)
107. Charlie Victor Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. Scaling LLM test-time compute optimally can be more effective than scaling parameters for reasoning. In The Thirteenth International Conference on Learning Representations, 2025. URL [https://openreview.net/forum?id=4FWAwZtd2n](https://openreview.net/forum?id=4FWAwZtd2n). [↗](https://openreview.net/forum?id=4FWAwZtd2n)
108. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. [Recursive deep models for semantic compositionality over a sentiment treebank](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631–1642, Se…
109. Hans Stuyck, Bart Aben, Axel Cleeremans, and Eva Van den Bussche. The aha! moment: Is insight a different form of problem solving? Consciousness and Cognition, 90:103055, 2021. ISSN 1053-8100. doi: https://doi.org/10.1016/j.concog.2020.103055. URL https://www.sciencedirect.com/science/ article/pii/S… — [doi:10.1016/j.concog.2020.103055](https://doi.org/10.1016/j.concog.2020.103055) [↗](https://doi.org/10.1016/j.concog.2020.103055)
110. Kumar Tanmay, Aditi Khandelwal, Utkarsh Agarwal, and Monojit Choudhury. Probing the moral development of large language models through defining issues test. arXiv preprint arXiv:2309.13356, 2023. — [arXiv:2309.13356](https://arxiv.org/abs/2309.13356) [find](https://scholar.google.com/scholar?q=Kumar+Tanmay%2C+Aditi+Khandelwal%2C+Utkarsh+Agarwal%2C+and+Monojit+Choudhury%2E+Probing+the+moral+development+of+large+language+models+through+defining+issues+test%2E+arXiv+preprint+arXiv%3A2309%2E13356%2C+2023%2E+%E2%80%94+%5Ba)
111. Stephen J Thoma. Research on the defining issues test. Handbook of moral development, pp. 85–110, 2006. [find](https://scholar.google.com/scholar?q=Stephen+J+Thoma%2E+Research+on+the+defining+issues+test%2E+Handbook+of+moral+development%2C+pp%2E+85%E2%80%93110%2C+2006%2E)
112. Matthew J Traxler. Trends in syntactic parsing: Anticipation, bayesian estimation, and good-enough parsing. Trends in cognitive sciences, 18(11):605–611, 2014. [find](https://scholar.google.com/scholar?q=Matthew+J+Traxler%2E+Trends+in+syntactic+parsing%3A+Anticipation%2C+bayesian+estimation%2C+and+good%2Denough+parsing%2E+Trends+in+cognitive+sciences%2C+18%2811%29%3A605%E2%80%93611%2C+2014%2E)
113. Luong Trung, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, and Hang Li. [ReFT: Reasoning with reinforced fine-tuning](https://md.research.elamur.ai/free/en/papers/trung-2024-reft-reasoning-reinforced-fine-tuning/). In Lun-Wei Ku, Andre Martins, and Vivek Srikumar (eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7601–…
114. Keyon Vafa, Justin Chen, Ashesh Rambachan, Jon Kleinberg, and Sendhil Mullainathan. Evaluating the world model implicit in a generative model. Advances in Neural Information Processing Systems, 37: 26941–26975, 2024. [find](https://scholar.google.com/scholar?q=Keyon+Vafa%2C+Justin+Chen%2C+Ashesh+Rambachan%2C+Jon+Kleinberg%2C+and+Sendhil+Mullainathan%2E+Evaluating+the+world+model+implicit+in+a+generative+model%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A+26)
115. Hemish Veeraboina. AIME problem set 1983-2024, 2023. hemishveeraboina/aime-problem-set-1983-2024. [find](https://scholar.google.com/scholar?q=Hemish+Veeraboina%2E+AIME+problem+set+1983%2D2024%2C+2023%2E+hemishveeraboina%2Faime%2Dproblem%2Dset%2D1983%2D2024%2E)
116. URL [https://www.kaggle.com/datasets/Matthew](https://www.kaggle.com/datasets/Matthew) W. Wagers, Ellen F. Lau, and Colin Phillips. Agreement attraction in comprehension: Representations and processes. Journal of Memory and Language, 61(2):206–237, August 2009. ISSN 0749596X. doi: 10.1016/j.jml.2009.04.002. URL https://linkinghub.elsevier.co… — [doi:10.1016/j.jml.2009.04.002](https://doi.org/10.1016/j.jml.2009.04.002) [↗](https://www.kaggle.com/datasets/Matthew)
117. Ziyu Wan, Xidong Feng, Muning Wen, Stephen Marcus McAleer, Ying Wen, Weinan Zhang, and Jun Wang. AlphaZero-like tree-search can guide large language model decoding and training. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org, 2024. [find](https://scholar.google.com/scholar?q=Ziyu+Wan%2C+Xidong+Feng%2C+Muning+Wen%2C+Stephen+Marcus+McAleer%2C+Ying+Wen%2C+Weinan+Zhang%2C+and+Jun+Wang%2E+AlphaZero%2Dlike+tree%2Dsearch+can+guide+large+language+model+decoding+and+training%2E+In+Proceedings+of+the+)
118. Boshi Wang, Sewon Min, Xiang Deng, Jiaming Shen, You Wu, Luke Zettlemoyer, and Huan Sun. [Towards understanding chain-of-thought prompting: An empirical study of what matters](https://md.research.elamur.ai/free/en/papers/wang-2023-understanding-chain-thought-prompting-empirical/). In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association for…
119. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). In The Eleventh International Conference on Learning Representations, 2023b. URL [https://openreview.net/forum?](https://openreview.net/forum?) i… [↗](https://openreview.net/forum?)
120. Yike Wang, Shangbin Feng, Heng Wang, Weijia Shi, Vidhisha Balachandran, Tianxing He, and Yulia Tsvetkov. [Resolving knowledge conflicts in large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-resolving-knowledge-conflicts-large-language/). In First Conference on Language Modeling, 2024. URL [https://openreview.net/forum?id=ptvV5HGTNN](https://openreview.net/forum?id=ptvV5HGTNN). [↗](https://openreview.net/forum?id=ptvV5HGTNN)
121. Yingxu Wang and Vincent Chiew. On the cognitive process of human problem solving. Cognitive Systems Research, 11(1):81–92, 2010. ISSN 1389-0417. doi: https://doi.org/10.1016/j.cogsys.2008.08.003. URL https://www.sciencedirect.com/science/article/pii/S1389041708000417. Brain Informatics. — [doi:10.1016/j.cogsys.2008.08.003](https://doi.org/10.1016/j.cogsys.2008.08.003) [↗](https://doi.org/10.1016/j.cogsys.2008.08.003)
122. Gloria S. Waters and David Caplan. Processing resource capacity and the comprehension of garden path sentences. Memory & Cognition, 24(3):342–355, May 1996. ISSN 0090-502X, 1532-5946. doi: 10.3758/ BF03213298. URL [http://link.springer.com/10.3758/BF03213298](http://link.springer.com/10.3758/BF03213298). — [doi:10.3758/bf03213298](https://doi.org/10.3758/bf03213298) [↗](http://link.springer.com/10.3758/BF03213298)
123. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824–24837, 2022.
124. Jerry Wei, Jason Wei, Yi Tay, Dustin Tran, Albert Webson, Yifeng Lu, Xinyun Chen, Hanxiao Liu, Da Huang, Denny Zhou, and Tengyu Ma. [Larger language models do in-context learning differently](https://md.research.elamur.ai/free/en/papers/wei-2023-larger-language-models-context-learning/), 2024. URL [https://openreview.net/forum?id=DRGnEkbiQZ](https://openreview.net/forum?id=DRGnEkbiQZ). [↗](https://openreview.net/forum?id=DRGnEkbiQZ)
125. Robert W. Weisberg. Toward an integrated theory of insight in problem solving. Thinking & Reasoning, 21 (1):5–39, 2015. doi: 10.1080/13546783.2014.886625. URL https://doi.org/10.1080/13546783.2014. 886625. — [doi:10.1080/13546783.2014.886625](https://doi.org/10.1080/13546783.2014.886625) [↗](https://doi.org/10.1080/13546783.2014)
126. Alexis Wellwood, Roumyana Pancheva, Valentine Hacquard, and Colin Phillips. The Anatomy of a Comparative Illusion. Journal of Semantics, 35(3):543–583, August 2018. ISSN 0167-5133, 1477-4593. doi: 10.1093/jos/ffy014. URL [https://academic.oup.com/jos/article/35/3/543/5065172](https://academic.oup.com/jos/article/35/3/543/5065172). — [doi:10.1093/jos/ffy014](https://doi.org/10.1093/jos/ffy014) [↗](https://academic.oup.com/jos/article/35/3/543/5065172)
127. Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, and Jun Zhao. [Large language models are better reasoners with self-verification](https://md.research.elamur.ai/free/en/papers/weng-2023-large-language-models-are-better/). In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 2550…
128. Ethan Wilcox, Pranali Vani, and Roger Levy. A targeted assessment of incremental processing in neural language models and humans. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Vol… [find](https://scholar.google.com/scholar?q=Ethan+Wilcox%2C+Pranali+Vani%2C+and+Roger+Levy%2E+A+targeted+assessment+of+incremental+processing+in+neural+language+models+and+humans%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Compu)
129. Violet Xiang, Charlie Snell, Kanishk Gandhi, Alon Albalak, Anikait Singh, Chase Blagden, Duy Phung, Rafael Rafailov, Nathan Lile, Dakota Mahan, Louis Castricato, Jan-Philipp Franken, Nick Haber, and Chelsea Finn. [Towards system 2 reasoning in llms: Learning how to think with meta chain-of-thought](https://md.research.elamur.ai/free/en/papers/xiang-2025-towards-system-2-reasoning-llms/), 2…
130. Rongwu Xu, Zehan Qi, Zhijiang Guo, Cunxiang Wang, Hongru Wang, Yue Zhang, and Wei Xu. [Knowledge conflicts for LLMs: A survey](https://md.research.elamur.ai/free/en/papers/xu-2024-knowledge-conflicts-llms-survey/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 8541–8565, 2024.
131. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… — [Qwen3 Technical Report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/)
132. Edward Yeo, Yuxuan Tong, Morry Niu, Graham Neubig, and Xiang Yue. [Demystifying long chain-of-thought reasoning in LLMs](https://md.research.elamur.ai/free/en/papers/yeo-2025-demystifying-long-chain-thought-reasoning/), 2025. URL https://arxiv.org/abs/2502.03373. [↗](https://arxiv.org/abs/2502.03373)
133. Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, and Asli Celikyilmaz. ALERT: Adapt language models to reasoning tasks. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association… [find](https://scholar.google.com/scholar?q=Ping+Yu%2C+Tianlu+Wang%2C+Olga+Golovneva%2C+Badr+AlKhamissi%2C+Siddharth+Verma%2C+Zhijing+Jin%2C+Gargi+Ghosh%2C+Mona+Diab%2C+and+Asli+Celikyilmaz%2E+ALERT%3A+Adapt+language+models+to+reasoning+tasks%2E+In+Anna+Rogers%2C+Jord)
134. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah D. Goodman. STaR: self-taught reasoner bootstrapping reasoning with reasoning. In Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS ’22, Red Hook, NY, USA, 2022. Curran Associates Inc. ISBN 9781713871088. [find](https://scholar.google.com/scholar?q=Eric+Zelikman%2C+Yuhuai+Wu%2C+Jesse+Mu%2C+and+Noah+D%2E+Goodman%2E+STaR%3A+self%2Dtaught+reasoner+bootstrapping+reasoning+with+reasoning%2E+In+Proceedings+of+the+36th+International+Conference+on+Neural+Information+Pr)
135. Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin, Yunhua Zhou, and Xipeng Qiu. [Revisiting the test-time scaling of o1-like models: Do they truly possess test-time scaling capabilities?](https://md.research.elamur.ai/free/en/papers/zeng-2025-revisiting-test-time-scaling-o1/), 2025. URL https://arxiv.org/abs/2502.12215. [↗](https://arxiv.org/abs/2502.12215)
136. Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue, Yuxiao Dong, and Jie Tang. [ReST-MCTS*: LLM self-training via process reward guided tree search](https://md.research.elamur.ai/free/en/papers/zhang-2024-rest-mcts-llm-self-training/). In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (eds.), Advances in Neural Information Processing Systems, volume 37,…
137. Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba Alabi, Xiaoyu Shen, Dietrich Klakow, and Marius Mosbach. The impact of demonstrations on multilingual in-context learning: A multidimensional analysis. In Lun-Wei Ku, Andre Martins, and Vivek Srikumar (eds.), Findings of the Association for Comp… [find](https://scholar.google.com/scholar?q=Miaoran+Zhang%2C+Vagrant+Gautam%2C+Mingyang+Wang%2C+Jesujoba+Alabi%2C+Xiaoyu+Shen%2C+Dietrich+Klakow%2C+and+Marius+Mosbach%2E+The+impact+of+demonstrations+on+multilingual+in%2Dcontext+learning%3A+A+multidimensional+ana)
138. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, and Shuming Shi. Siren’s song in the AI ocean: A survey on hallucination in large language models, 2023a. [URL https://arxiv.org/abs/2309.…](https://md.research.elamur.ai/free/en/papers/zhang-2023-siren-s-song-ai-ocean/) [↗](https://arxiv.org/abs/2309.…)
139. Yuhan Zhang, Edward Gibson, and Forrest Davis. Can language models be tricked by language illusions? easier with syntax, harder with semantics. In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pp. 1–14, Singapore, 2023b. Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Yuhan+Zhang%2C+Edward+Gibson%2C+and+Forrest+Davis%2E+Can+language+models+be+tricked+by+language+illusions%3F+easier+with+syntax%2C+harder+with+semantics%2E+In+Proceedings+of+the+27th+Conference+on+Computational+N)
140. Yuhan Zhang, Carina Kauf, Roger Philip Levy, and Edward Gibson. Comparative illusions are evidence of rational inference in language comprehension, May 2024c. URL [https://osf.io/efr3q](https://osf.io/efr3q). [↗](https://osf.io/efr3q)
141. Tianyang Zhong, Zhengliang Liu, Yi Pan, Yutong Zhang, Yifan Zhou, Shizhe Liang, Zihao Wu, Yanjun Lyu, Peng Shu, Xiaowei Yu, et al. [Evaluation of OpenAI o1: Opportunities and challenges of AGI](https://md.research.elamur.ai/free/en/papers/zhong-2024-evaluation-openai-o1-opportunities-challenges/). arXiv preprint arXiv:2409.18486, 2024.
142. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V Le, and Ed H. Chi. [Least-to-most prompting enables complex reasoning in large language models](https://md.research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/). In The Eleventh International Conference on Learning Representations, 202…
143. Hattie Zhou, Azade Nova, Hugo Larochelle, Aaron Courville, Behnam Neyshabur, and Hanie Sedghi. [Teaching algorithmic reasoning via in-context learning](https://md.research.elamur.ai/free/en/papers/zhou-2022-teaching-algorithmic-reasoning-context-learning/), 2022. URL https://arxiv.org/abs/2211.09066. [↗](https://arxiv.org/abs/2211.09066)

*Updated 3 November 2026*