---
title: "CLARO — paper by Schlesinger et al. (2026)"
description: "They then propose CLARO, a reinforcement learning framework that trains models to adopt four interpretable, cheaply… 55 references."
authors: ["Oded Schlesinger", "Young Kyung Kim", "J. Matias Di Martino", "Guillermo Sapiro"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1335/"
doi: "10.18653/v1/2026.findings-acl.1335"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/schlesinger-2026-claro-controlled-attribute-driven-reasoning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/schlesinger-2026-claro-controlled-attribute-driven-reasoning/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) / CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought

# CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought

**Authors:** Oded Schlesinger, Young Kyung Kim, J. Matias Di Martino and Guillermo Sapiro · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1335/) · [PDF](https://aclanthology.org/2026.findings-acl.1335.pdf) · [DOI 10.18653/v1/2026.findings-acl.1335](https://doi.org/10.18653/v1/2026.findings-acl.1335) · [OpenAlex](https://openalex.org/W7166856058)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Reasoning LLMs often produce long, loosely organized Chain-of-Thought traces, which makes inference expensive. Existing remedies mostly shorten outputs through token penalties or truncation, and these can drop steps the model needs. The authors argue that brevity should result from better-structured reasoning rather than be imposed directly. They first show that Attribute-Guided Prompting, a zero-shot instruction asking the model to shape its reasoning along explicit structural attributes, raises accuracy while lowering token cost. They then propose CLARO, a reinforcement learning framework that trains models to adopt four interpretable, cheaply computed attributes: readability, math notation density, syntactic compression and low redundancy. Training also keeps outputs within a user-chosen token budget. Structural rewards are given only when the final answer is correct, which discourages gaming the proxy metrics. Across diverse benchmarks, CLARO outperforms state-of-the-art baselines, with accuracy gains of up to 63.6%. The advantage is largest under tight budgets. The work offers a transparent way to reduce reasoning cost without an opaque reward model, and it does so without sacrificing answer quality.

## Key points
- The paper has two components. Attribute-Guided Prompting is an inference-time, plug-and-play method that also helps widely used pretrained LLMs. CLARO is an RL fine-tuning method that internalizes the same attributes.
- The optimized attributes are readability, mathematical density, syntactic compression and redundancy. In the authors' analysis, correct answers consistently show higher readability, denser math and tighter syntax than wrong ones.
- CLARO reports accuracy gains of up to 63.6% over state-of-the-art baselines. The gains are biggest in restrictive token regimes but persist under generous and unconstrained budgets.
- Attribute targets calibrated on a 1.5B model transferred well to a 7B model. The metrics, especially the readability formulas, are tuned for English, so applying them to Ukrainian would require redefining them. The framework itself is language-agnostic.
- Code and models are available at https://github.com/odedsc/CLARO.

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

## Institutions

- [Princeton University](https://md.research.elamur.ai/free/en/universities/princeton-university/) — University, Princeton, United States · 90 works · 39,109 citations
- [Duke University](https://md.research.elamur.ai/free/en/universities/duke-university/) — University, Durham, United States · 28 works · 15,077 citations
- [Apple](https://md.research.elamur.ai/free/en/companies/apple/) — Company, Cupertino, United States · 20 works · 2,146 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Oded Schlesinger, Young Kyung Kim, J. Matias Di Martino and Guillermo Sapiro. 2026. CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{schlesinger2026claro,
  title = {{CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought}},
  author = {Oded Schlesinger, Young Kyung Kim, J. Matias {Di Martino} and Guillermo Sapiro},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1335},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1335}
}
```

- [← previous CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems](https://md.research.elamur.ai/free/en/papers/sarwar-2026-clarity-framework-benchmark-conversational-language/)
- [next → ClarVis: A Dataset of Clarification Requests and Grounding in Collaborative Data Visualization Dialogues](https://md.research.elamur.ai/free/en/papers/bhattacharya-2026-clarvis-dataset-clarification-requests-grounding/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/)

## References

55 references, 34 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J Hewett, Mojan Javaheripi, Piero Kauffmann, and 1 others. 2024. [Phi-4 technical report](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-4-technical-report/). arXiv preprint arXiv:2412.08905.
2. Pranjal Aggarwal and Sean Welleck. 2025. [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/). arXiv preprint arXiv:2503.04697.
3. Daman Arora and Andrea Zanette. 2025. Training language models to reason efficiently. arXiv preprint arXiv:2502.04463. [find](https://scholar.google.com/scholar?q=Daman+Arora+and+Andrea+Zanette%2E+2025%2E+Training+language+models+to+reason+efficiently%2E+arXiv+preprint+arXiv%3A2502%2E04463%2E)
4. Zhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang, and Yunhe Wang. 2024. [Forest-of-thought: Scaling test-time compute for enhancing LLM reasoning](https://md.research.elamur.ai/free/en/papers/bi-2024-forest-thought-scaling-test-time/). arXiv preprint arXiv:2412.09078.
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in Neural Information Processing Systems, 33:1877–1901.
6. [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/). arXiv preprint arXiv:2501.12948.
7. Michael Hassid, Gabriel Synnaeve, Yossi Adi, and Roy Schwartz. 2025. Don’t overthink it. Preferring shorter thinking chains for improved LLM reasoning. arXiv preprint arXiv:2505.17813. — [arXiv:2505.17813](https://arxiv.org/abs/2505.17813) [find](https://scholar.google.com/scholar?q=Michael+Hassid%2C+Gabriel+Synnaeve%2C+Yossi+Adi%2C+and+Roy+Schwartz%2E+2025%2E+Don%E2%80%99t+overthink+it%2E+Preferring+shorter+thinking+chains+for+improved+LLM+reasoning%2E+arXiv+preprint+arXiv%3A2505%2E17813%2E+%E2%80%94+%5BarXiv%3A2505%2E1)
8. Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, and 1 others. 2024. [Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems](https://md.research.elamur.ai/free/en/papers/he-2024-olympiadbench-challenging-benchmark-promoting-agi/). arXiv preprint arXiv:2402.14008.
9. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). arXiv preprint arXiv:2009.03300.
10. Bairu Hou, Yang Zhang, Jiabao Ji, Yujian Liu, Kaizhi Qian, Jacob Andreas, and Shiyu Chang. 2025. [Thinkprune: Pruning long Chain-of-Thought of LLMs via reinforcement learning](https://md.research.elamur.ai/free/en/papers/hou-2025-thinkprune-pruning-long-chain-thought/). arXiv preprint arXiv:2504.01296.
11. Sondos Mahmoud Bsharat, Aidar Myrzakhan, and Zhiqiang Shen. 2023. Principled instructions are all you need for questioning Llama-1/2, GPT-3.5/4. arXiv preprint arXiv:2312.16171. — [arXiv:2312.16171](https://arxiv.org/abs/2312.16171) [find](https://scholar.google.com/scholar?q=Sondos+Mahmoud+Bsharat%2C+Aidar+Myrzakhan%2C+and+Zhiqiang+Shen%2E+2023%2E+Principled+instructions+are+all+you+need+for+questioning+Llama%2D1%2F2%2C+GPT%2D3%2E5%2F4%2E+arXiv+preprint+arXiv%3A2312%2E16171%2E+%E2%80%94+%5BarXiv%3A2312%2E16171%5D%28h)
12. William Jurayj, Jeffrey Cheng, and Benjamin Van Durme. 2025. [Is that your final answer? Test-time scaling improves selective question answering](https://md.research.elamur.ai/free/en/papers/jurayj-2025-is-that-your-final-answer/). arXiv preprint arXiv:2502.13962.
13. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2022. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Xueguang+Ma%2C+Xinyi+Wang%2C+and+William+W+Cohen%2E+2022%2E+Program+of+thoughts+prompting%3A+Disentangling+computation+from+reasoning+for+numerical+reasoning+tasks%2E+arXiv+preprint+arXiv%3A2211%2E12588%2E)
14. Yu Kang, Xianghui Sun, Liangyu Chen, and Wei Zou. 2025. C3ot: Generating shorter Chain-of-Thought without compromising effectiveness. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 24312–24320. [find](https://scholar.google.com/scholar?q=Yu+Kang%2C+Xianghui+Sun%2C+Liangyu+Chen%2C+and+Wei+Zou%2E+2025%2E+C3ot%3A+Generating+shorter+Chain%2Dof%2DThought+without+compromising+effectiveness%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+)
15. Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, and 1 others. 2024. [Do not think that much for 2+3=? on the overthinking of o1-like LLMs](https://md.research.elamur.ai/free/en/papers/chen-2024-think-that-much-2-3/). arXiv preprint arXiv:2412.21187.
16. J Peter Kincaid, Robert P Fishburne Jr, Richard L Rogers, and Brad S Chissom. 1975. Derivation of new readability formulas (automated readability index, fog count and Flesch reading ease formula) for navy enlisted personnel. [find](https://scholar.google.com/scholar?q=J+Peter+Kincaid%2C+Robert+P+Fishburne+Jr%2C+Richard+L+Rogers%2C+and+Brad+S+Chissom%2E+1975%2E+Derivation+of+new+readability+formulas+%28automated+readability+index%2C+fog+count+and+Flesch+reading+ease+formula%29+for+)
17. Cheng-Han Chiang and Hung-yi Lee. 2024. [Over-reasoning and redundant calculation of large language models](https://md.research.elamur.ai/free/en/papers/chiang-2024-over-reasoning-redundant-calculation-large/). arXiv preprint arXiv:2401.11467.
18. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 2021. [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.
19. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The Llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
20. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Ruoyu+Zhang%2C+Runxin+Xu%2C+Qihao+Zhu%2C+Shirong+Ma%2C+Peiyi+Wang%2C+Xiao+Bi%2C+and+1+others%2E+2025%2E)
21. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in Neural Information Processing Systems, 35:22199– 22213.
22. Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, and Nazneen Fatema Rajani. 2020. [Gedi: Generative discriminator guided sequence generation](https://md.research.elamur.ai/free/en/papers/krause-2021-gedi-generative-discriminator-guided-sequence/). arXiv preprint arXiv:2009.06367.
23. Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, and 1 others. 2022. [Solving quantitative reasoning problems with language models](https://md.research.elamur.ai/free/en/papers/lewkowycz-2022-solving-quantitative-reasoning-problems-language/). Advances in Neural Information Processing Systems, 35:3843–3857…
24. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
25. Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A Smith, and Yejin Choi. 2021. [Dexperts: Decoding-time controlled text generation with experts and anti-experts](https://md.research.elamur.ai/free/en/papers/liu-2021-dexperts-decoding-time-controlled-text/). arXiv preprint arXiv:2105.03023.
26. Ximing Lu, Sean Welleck, Jack Hessel, Liwei Jiang, Lianhui Qin, Peter West, Prithviraj Ammanabrolu, and Yejin Choi. 2022. [Quark: Controllable text generation with reinforced unlearning](https://md.research.elamur.ai/free/en/papers/lu-2022-quark-controllable-text-generation-reinforced/). Advances in Neural Information Processing Systems, 35:27591– 27609.
27. Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao. 2025a. O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning. arXiv preprint arXiv:2501.12570. [find](https://scholar.google.com/scholar?q=Haotian+Luo%2C+Li+Shen%2C+Haiying+He%2C+Yibo+Wang%2C+Shiwei+Liu%2C+Wei+Li%2C+Naiqiang+Tan%2C+Xiaochun+Cao%2C+and+Dacheng+Tao%2E+2025a%2E+O1%2Dpruner%3A+Length%2Dharmonizing+fine%2Dtuning+for+o1%2Dlike+reasoning+pruning%2E+arXiv+prep)
28. Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, and 1 others. 2025b. Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl. Notion Blog. [find](https://scholar.google.com/scholar?q=Michael+Luo%2C+Sijun+Tan%2C+Justin+Wong%2C+Xiaoxiang+Shi%2C+William+Y+Tang%2C+Manan+Roongta%2C+Colin+Cai%2C+Jeffrey+Luo%2C+Tianjun+Zhang%2C+Li+Erran+Li%2C+and+1+others%2E+2025b%2E+Deepscaler%3A+Surpassing+o1%2Dpreview+with+a+1%2E5)
29. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, and 1 others. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36:46534–46594. [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+and+1+others%2E+2023%2E+Self%2Drefine%3A+Iterative+refinement+with)
30. David M Markowitz. 2024. From complexity to clarity: How ai enhances perceptions of scientists and the public’s understanding of science. PNAS Nexus, 3(9):pgae387. [find](https://scholar.google.com/scholar?q=David+M+Markowitz%2E+2024%2E+From+complexity+to+clarity%3A+How+ai+enhances+perceptions+of+scientists+and+the+public%E2%80%99s+understanding+of+science%2E+PNAS+Nexus%2C+3%289%29%3Apgae387%2E)
31. Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, and Mehrdad Farajtabar. 2024. [Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models](https://md.research.elamur.ai/free/en/papers/mirzadeh-2024-gsm-symbolic-understanding-limitations-mathematical/). arXiv preprint arXiv:2410.05229.
32. Mistral AI. 2024. Mathstral. Accessed: 2025-12-04. [find](https://scholar.google.com/scholar?q=Mistral+AI%2E+2024%2E+Mathstral%2E+Accessed%3A+2025%2D12%2D04%2E)
33. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. 2025. [s1: Simple test-time scaling](https://md.research.elamur.ai/free/en/papers/muennighoff-2025-s1-simple-test-time-scaling/). arXiv preprint arXiv:2501.19393.
34. Sania Nayab, Giulio Rossolini, Marco Simoni, Andrea Saracino, Giorgio Buttazzo, Nicolamaria Manes, and Fabrizio Giacomelli. 2024. Concise thoughts: Impact of output length on LLM reasoning and cost. arXiv preprint arXiv:2407.19825. — [arXiv:2407.19825](https://arxiv.org/abs/2407.19825) [find](https://scholar.google.com/scholar?q=Sania+Nayab%2C+Giulio+Rossolini%2C+Marco+Simoni%2C+Andrea+Saracino%2C+Giorgio+Buttazzo%2C+Nicolamaria+Manes%2C+and+Fabrizio+Giacomelli%2E+2024%2E+Concise+thoughts%3A+Impact+of+output+length+on+LLM+reasoning+and+cost%2E+a)
35. OpenAI. 2024. Learning to Reason with LLMs. Accessed: 2025-12-04. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Learning+to+Reason+with+LLMs%2E+Accessed%3A+2025%2D12%2D04%2E)
36. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in Neural Information Processing Systems, 35:27730–27744.
37. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in Neural Information Processing Systems, 36:53728– 53741.
38. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. 2024. [Gpqa: A graduate-level Google-proof Q&A benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling.
39. Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information Processing & Management, 24(5):513– 523. [find](https://scholar.google.com/scholar?q=Gerard+Salton+and+Christopher+Buckley%2E+1988%2E+Term%2Dweighting+approaches+in+automatic+text+retrieval%2E+Information+Processing+%26+Management%2C+24%285%29%3A513%E2%80%93+523%2E)
40. Timo Schick, Sahana Udupa, and Hinrich Schütze. 2021. [Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in NLP](https://md.research.elamur.ai/free/en/papers/schick-2021-self-diagnosis-self-debiasing-proposal/). Transactions of the Association for Computational Linguistics, 9:1408– 1424.
41. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 2024. [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/). arXiv preprint arXiv:2402.03300.
42. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2024. [Hybridflow: A flexible and efficient RLHF framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). arXiv preprint arXiv: 2409.19256.
43. Advaith Siddharthan. 2014. A survey of research on text simplification. ITL-International Journal of Applied Linguistics, 165(2):259–298. [find](https://scholar.google.com/scholar?q=Advaith+Siddharthan%2E+2014%2E+A+survey+of+research+on+text+simplification%2E+ITL%2DInternational+Journal+of+Applied+Linguistics%2C+165%282%29%3A259%E2%80%93298%2E)
44. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. [Scaling LLM test-time compute optimally can be more effective than scaling model parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/). arXiv preprint arXiv:2408.03314.
45. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [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.
46. Jason Weston and Sainbayar Sukhbaatar. 2023. System 2 attention (is something you might need too). arXiv preprint arXiv:2311.11829. 26790 12 — [arXiv:2311.11829](https://arxiv.org/abs/2311.11829) [find](https://scholar.google.com/scholar?q=Jason+Weston+and+Sainbayar+Sukhbaatar%2E+2023%2E+System+2+attention+%28is+something+you+might+need+too%29%2E+arXiv+preprint+arXiv%3A2311%2E11829%2E+26790+12+%E2%80%94+%5BarXiv%3A2311%2E11829%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2311%2E11829%29)
47. Heming Xia, Chak Tou Leong, Wenjie Wang, Yongqi Li, and Wenjie Li. 2025. [Tokenskip: Controllable Chain-of-Thought compression in LLMs](https://md.research.elamur.ai/free/en/papers/xia-2025-tokenskip-controllable-chain-thought-compression/). arXiv preprint arXiv:2502.12067.
48. Silei Xu, Wenhao Xie, Lingxiao Zhao, and Pengcheng He. 2025. Chain of draft: Thinking faster by writing less. arXiv preprint arXiv:2502.18600. [find](https://scholar.google.com/scholar?q=Silei+Xu%2C+Wenhao+Xie%2C+Lingxiao+Zhao%2C+and+Pengcheng+He%2E+2025%2E+Chain+of+draft%3A+Thinking+faster+by+writing+less%2E+arXiv+preprint+arXiv%3A2502%2E18600%2E)
49. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 40 others. 2024. Qwen2 technical report. arXiv preprint arXi… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)
50. Wenkai Yang, Shuming Ma, Yankai Lin, and Furu Wei. 2025. [Towards thinking-optimal scaling of test-time compute for LLM reasoning](https://md.research.elamur.ai/free/en/papers/yang-2025-towards-thinking-optimal-scaling-test/). arXiv preprint arXiv:2502.18080.
51. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36:11809–11822. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+Neural+Inf)
52. Weizhe Yuan, Ilia Kulikov, Ping Yu, Kyunghyun Cho, Sainbayar Sukhbaatar, Jason Weston, and Jing Xu. 2024. [Following length constraints in instructions](https://md.research.elamur.ai/free/en/papers/yuan-2025-following-length-constraints-instructions/). arXiv preprint arXiv:2406.17744.
53. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. 2022. [Star: Bootstrapping reasoning with reasoning](https://md.research.elamur.ai/free/en/papers/zelikman-2022-star-bootstrapping-reasoning-reasoning/). Advances in Neural Information Processing Systems, 35:15476–15488.
54. Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin, Ming Zhou, and Nan Duan. 2022. Analytical reasoning of text. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2306–2319. [find](https://scholar.google.com/scholar?q=Wanjun+Zhong%2C+Siyuan+Wang%2C+Duyu+Tang%2C+Zenan+Xu%2C+Daya+Guo%2C+Yining+Chen%2C+Jiahai+Wang%2C+Jian+Yin%2C+Ming+Zhou%2C+and+Nan+Duan%2E+2022%2E+Analytical+reasoning+of+text%2E+In+Findings+of+the+Association+for+Computatio)
55. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, and 1 others. 2022. [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/). arXiv preprint arXiv:2205.10625. 26791 13

*Updated 1 November 2026*