---
title: "GCoT-Decoding — paper by Luo et al. (2026)"
description: "Chain-of-thought (CoT) reasoning usually depends on hand-crafted prompts. 46 references, cited by 6 papers here."
authors: ["Guanran Luo", "Wentao Qiu", "Zhongquan Jian", "Meihong Wang", "Qingqiang Wu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.319/"
doi: "10.18653/v1/2026.findings-acl.319"
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/luo-2026-gcot-decoding-unlocking-deep-reasoning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/luo-2026-gcot-decoding-unlocking-deep-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/3/) / GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering

# GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering

**Authors:** [Guanran Luo](https://md.research.elamur.ai/free/en/authors/guanran-luo/), [Wentao Qiu](https://md.research.elamur.ai/free/en/authors/wentao-qiu/), [Zhongquan Jian](https://md.research.elamur.ai/free/en/authors/zhongquan-jian/), [Meihong Wang](https://md.research.elamur.ai/free/en/authors/meihong-wang/) and [Qingqiang Wu](https://md.research.elamur.ai/free/en/authors/qingqiang-wu/) · **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.319/) · [PDF](https://aclanthology.org/2026.findings-acl.319.pdf) · [DOI 10.18653/v1/2026.findings-acl.319](https://doi.org/10.18653/v1/2026.findings-acl.319) · [OpenAlex](https://openalex.org/W7166851742)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [6](https://md.research.elamur.ai/free/en/papers/luo-2026-gcot-decoding-unlocking-deep-reasoning/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Chain-of-thought (CoT) reasoning usually depends on hand-crafted prompts. The earlier prompt-free CoT-decoding method only works when answers come from a fixed set, such as numbers, because it extracts an exact answer span and votes by string match. GCoT-decoding is a general decoding framework that removes this restriction so it can also handle free-form question answering.

It works in three layers:
- **Exploration:** first-step branches are seeded at Fibonacci-ranked candidate indices, which skips clusters of near-duplicate wrong continuations. Each path then gets one backtracking step at its first local confidence minimum.
- **Scoring:** each path is treated as a reasoning part followed by an answer part and scored with a length-aware top-2 logit gap. An optional LCS-based SpanAlign variant is also offered.
- **Aggregation:** paraphrase-equivalent answers are pooled through greedy semantic clustering instead of majority voting.

On six fixed-answer and free-form QA datasets, GCoT matches standard multi-path decoders on fixed-answer tasks and gives consistent gains on free-form ones. It also combines well with few-shot CoT prompting and reasoning-tuned models. This makes prompt-free reasoning elicitation usable beyond tasks with a closed answer format.

## Key points
- Seeds use Fibonacci indices with F1=1 and F2=2, i.e. ranks 1, 2, 3, 5, 8, and so on. In one case study, the correct label ("historical wars") surfaced only at k=8.
- Ablations show that most of the gain comes from Fibonacci multi-path exploration plus greedy semantic clustering. Local-minimum backtracking adds a smaller but consistent improvement.
- Cost breakdown on GSM8K with Gemma-7B and k=10 (base generation time of 45.0 s per question):

  | Aggregation | Added time | Overhead | MATCH |
  |---|---|---|---|
  | Greedy clustering | 0.2 s | ~0.4% | 54.6 |
  | LLM-based aggregation | 8.3 s | ~18.4% | 35.8 |
  | No aggregation (MaxPath) | — | — | 21.8 |

- Total time grows roughly linearly with the number of paths k, while gains diminish. The best trade-off is around k=3–5.
- Limitations include extra compute from maintaining multiple paths and no evaluation on tasks with implicit reasoning, such as summarization.

*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

- [Xiamen University](https://md.research.elamur.ai/free/en/universities/xiamen-university/) — University, Xiamen, China · 21 works · 2,258 citations
- [Minjiang University](https://md.research.elamur.ai/free/en/universities/minjiang-university/) — University, Fuzhou, China · 2 works · 8 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 (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works

## Cite

Cite as: Guanran Luo, Wentao Qiu, Zhongquan Jian, Meihong Wang and Qingqiang Wu. 2026. GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering. 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{luo2026gcot,
  title = {{GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering}},
  author = {Guanran Luo, Wentao Qiu, Zhongquan Jian, Meihong Wang and Qingqiang Wu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.319},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.319}
}
```

- [← previous GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/hu-2026-gambit-gamified-jailbreak-framework-multimodal/)
- [next → Glyph: Scaling Context Windows via Visual-Text Compression](https://md.research.elamur.ai/free/en/papers/cheng-2026-glyph-scaling-context-windows-visual/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/)

## References

46 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Simran Arora, Avanika Narayan, Mayee F Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, and Christopher Ré. 2022. Ask me anything: A simple strategy for prompting language models. arXiv preprint arXiv:2210.02441. [find](https://scholar.google.com/scholar?q=Simran+Arora%2C+Avanika+Narayan%2C+Mayee+F+Chen%2C+Laurel+Orr%2C+Neel+Guha%2C+Kush+Bhatia%2C+Ines+Chami%2C+Frederic+Sala%2C+and+Christopher+R%C3%A9%2E+2022%2E+Ask+me+anything%3A+A+simple+strategy+for+prompting+language+models%2E+)
2. Fahao Chen, Peng Li, Tom H Luan, Zhou Su, and Jing Deng. 2025. Spin: Accelerating large language model inference with heterogeneous speculative models. arXiv preprint arXiv:2503.15921. [find](https://scholar.google.com/scholar?q=Fahao+Chen%2C+Peng+Li%2C+Tom+H+Luan%2C+Zhou+Su%2C+and+Jing+Deng%2E+2025%2E+Spin%3A+Accelerating+large+language+model+inference+with+heterogeneous+speculative+models%2E+arXiv+preprint+arXiv%3A2503%2E15921%2E)
3. Wenqing Chen, Weicheng Wang, Zhixuan Chu, Kui Ren, Zibin Zheng, and Zhichao Lu. 2024. Self-paraconsistency: Improving reasoning tasks at low cost for large language models. In 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), pages 14162–14167. Association for Computat… [find](https://scholar.google.com/scholar?q=Wenqing+Chen%2C+Weicheng+Wang%2C+Zhixuan+Chu%2C+Kui+Ren%2C+Zibin+Zheng%2C+and+Zhichao+Lu%2E+2024%2E+Self%2Dparaconsistency%3A+Improving+reasoning+tasks+at+low+cost+for+large+language+models%2E+In+62nd+Annual+Meeting+of+t)
4. 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.
5. Shizhe Diao, Pengcheng Wang, Yong Lin, Rui Pan, Xiang Liu, and Tong Zhang. 2023. Active prompting with chain-of-thought for large language models. arXiv preprint arXiv:2302.12246. [find](https://scholar.google.com/scholar?q=Shizhe+Diao%2C+Pengcheng+Wang%2C+Yong+Lin%2C+Rui+Pan%2C+Xiang+Liu%2C+and+Tong+Zhang%2E+2023%2E+Active+prompting+with+chain%2Dof%2Dthought+for+large+language+models%2E+arXiv+preprint+arXiv%3A2302%2E12246%2E)
6. Xueren Ge, Sahil Murtaza, Anthony Cortez, and Homa Alemzadeh. 2025. Expert-guided prompting and retrieval-augmented generation for emergency medical service question answering. Preprint, arXiv:2511.10900. — [arXiv:2511.10900](https://arxiv.org/abs/2511.10900) [find](https://scholar.google.com/scholar?q=Xueren+Ge%2C+Sahil+Murtaza%2C+Anthony+Cortez%2C+and+Homa+Alemzadeh%2E+2025%2E+Expert%2Dguided+prompting+and+retrieval%2Daugmented+generation+for+emergency+medical+service+question+answering%2E+Preprint%2C+arXiv%3A2511%2E10)
7. Xueren Ge, Sahil Murtaza, Anthony Cortez, and Homa Alemzadeh. 2026. Emsdialog: Synthetic multi-person emergency medical service dialogue generation from electronic patient care reports via multi-llm agents. Preprint, arXiv:2604.07549. [find](https://scholar.google.com/scholar?q=Xueren+Ge%2C+Sahil+Murtaza%2C+Anthony+Cortez%2C+and+Homa+Alemzadeh%2E+2026%2E+Emsdialog%3A+Synthetic+multi%2Dperson+emergency+medical+service+dialogue+generation+from+electronic+patient+care+reports+via+multi%2Dllm+a)
8. Olga Golovneva, Sean O’Brien, Ramakanth Pasunuru, Tianlu Wang, Luke Zettlemoyer, Maryam Fazel-Zarandi, and Asli Celikyilmaz. 2023. Pathfinder: Guided search over multi-step reasoning paths. arXiv preprint arXiv:2312.05180. [find](https://scholar.google.com/scholar?q=Olga+Golovneva%2C+Sean+O%E2%80%99Brien%2C+Ramakanth+Pasunuru%2C+Tianlu+Wang%2C+Luke+Zettlemoyer%2C+Maryam+Fazel%2DZarandi%2C+and+Asli+Celikyilmaz%2E+2023%2E+Pathfinder%3A+Guided+search+over+multi%2Dstep+reasoning+paths%2E+arXiv+prep)
9. 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.
10. Namgyu Ho, Laura Schmid, and Se-Young Yun. 2022. [Large language models are reasoning teachers](https://md.research.elamur.ai/free/en/papers/ho-2023-large-language-models-are-reasoning/). arXiv preprint arXiv:2212.10071.
11. Hongru Ji, Yuyin Fan, Meng Zhao, Xianghua Li, Lianwei Wu, and Chao Gao. 2026. [Stride-ed: A strategy-grounded stepwise reasoning framework for empathetic dialogue systems](https://md.research.elamur.ai/free/en/papers/ji-2026-stride-ed-strategy-grounded-stepwise/). Preprint, arXiv:2604.07100.
12. Fengqing Jiang. 2024. Identifying and mitigating vulnerabilities in llm-integrated applications. Master’s thesis, University of Washington. [find](https://scholar.google.com/scholar?q=Fengqing+Jiang%2E+2024%2E+Identifying+and+mitigating+vulnerabilities+in+llm%2Dintegrated+applications%2E+Master%E2%80%99s+thesis%2C+University+of+Washington%2E)
13. 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.
14. Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, and Mike Lewis. 2022. [Contrastive decoding: Open-ended text generation as optimization](https://md.research.elamur.ai/free/en/papers/li-2022-contrastive-decoding-open-ended-text/). arXiv preprint arXiv:2210.15097.
15. 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.
16. Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, and Hao Su. 2023. [Deductive verification of chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/ling-2023-deductive-verification-chain-thought-reasoning/). Advances in Neural Information Processing Systems, 36:36407–36433.
17. Hongye Liu and Ricardo Henao. 2025. Learning to substitute words with model-based score ranking. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 11551–11565. [find](https://scholar.google.com/scholar?q=Hongye+Liu+and+Ricardo+Henao%2E+2025%2E+Learning+to+substitute+words+with+model%2Dbased+score+ranking%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Americas+Chapter+of+the+Association+for+Com)
18. Qing Lyu, Shreya Havaldar, Adam Stein, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, and Chris Callison-Burch. 2023. [Faithful chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/lyu-2023-faithful-chain-thought-reasoning/). In The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Associa…
19. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
20. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [Squad: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). arXiv preprint arXiv:1606.05250.
21. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). arXiv preprint arXiv:1908.10084.
22. Subhro Roy and Dan Roth. 2015. [Solving general arithmetic word problems](https://md.research.elamur.ai/free/en/papers/roy-2015-solving-general-arithmetic-word-problems/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1743–1752, Lisbon, Portugal. Association for Computational Linguistics.
23. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Synthetic prompting: Generating chain-of-thought demonstrations for large language models. In International Conference on Machine Learning, pages 30706–30775. PMLR. [find](https://scholar.google.com/scholar?q=Zhihong+Shao%2C+Yeyun+Gong%2C+Yelong+Shen%2C+Minlie+Huang%2C+Nan+Duan%2C+and+Weizhu+Chen%2E+2023%2E+Synthetic+prompting%3A+Generating+chain%2Dof%2Dthought+demonstrations+for+large+language+models%2E+In+International+Confer)
24. Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, and Wen-tau Yih. 2024. [Trusting your evidence: Hallucinate less with context-aware decoding](https://md.research.elamur.ai/free/en/papers/shi-2024-trusting-your-evidence-hallucinate-less/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language…
25. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, and 1 others. 2022. [Beyond the imitation game: Quantifying and extrapolating the capabilities of language models](https://md.research.elamur.ai/free/en/papers/srivastava-2022-imitation-game-quantifying-extrapolating-capabilities/). arXiv preprint arXiv:2206.…
26. Yuxi Sun, Aoqi Zuo, Haotian Xie, Wei Gao, Mingming Gong, and Jing Ma. 2026. [Fact-e: Causality-inspired evaluation for trustworthy chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/sun-2026-fact-e-causality-inspired-evaluation/). Preprint, arXiv:2604.10693.
27. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, , and Jason Wei. 2022. [Challenging big-bench tasks and whether chain-of-thought can solve them](https://md.research.elamur.ai/free/en/papers/suzgun-2023-challenging-big-bench-tasks-whether/). arXiv preprint arXiv:2210.09261.
28. Amir Taubenfeld, Tom Sheffer, Eran Ofek, Amir Feder, Ariel Goldstein, Zorik Gekhman, and Gal Yona. 2025. Confidence improves self-consistency in llms. arXiv preprint arXiv:2502.06233. [find](https://scholar.google.com/scholar?q=Amir+Taubenfeld%2C+Tom+Sheffer%2C+Eran+Ofek%2C+Amir+Feder%2C+Ariel+Goldstein%2C+Zorik+Gekhman%2C+and+Gal+Yona%2E+2025%2E+Confidence+improves+self%2Dconsistency+in+llms%2E+arXiv+preprint+arXiv%3A2502%2E06233%2E)
29. Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, and 1 others. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Thomas+Mesnard%2C+Cassidy+Hardin%2C+Robert+Dadashi%2C+Surya+Bhupatiraju%2C+Shreya+Pathak%2C+Laurent+Sifre%2C+Morgane+Rivi%C3%A8re%2C+Mihir+Sanjay+Kale%2C+Juliette+Love%2C+and+1+others%2E+2024%2E+Gemma%3A+Open+models+b)
30. Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. [Solving math word problems with process-and outcome-based feedback](https://md.research.elamur.ai/free/en/papers/uesato-2022-solving-math-word-problems-process/). arXiv preprint arXiv:2211.14275.
31. Han Wang, Archiki Prasad, Elias Stengel-Eskin, and Mohit Bansal. 2024. Soft self-consistency improves language model agents. arXiv preprint arXiv:2402.13212. [find](https://scholar.google.com/scholar?q=Han+Wang%2C+Archiki+Prasad%2C+Elias+Stengel%2DEskin%2C+and+Mohit+Bansal%2E+2024%2E+Soft+self%2Dconsistency+improves+language+model+agents%2E+arXiv+preprint+arXiv%3A2402%2E13212%2E)
32. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022a. [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/). arXiv preprint arXiv:2203.11171.
33. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. 2022b. Rationale-augmented ensembles in language models. arXiv preprint arXiv:2207.00747. [find](https://scholar.google.com/scholar?q=Xuezhi+Wang%2C+Jason+Wei%2C+Dale+Schuurmans%2C+Quoc+Le%2C+Ed+Chi%2C+and+Denny+Zhou%2E+2022b%2E+Rationale%2Daugmented+ensembles+in+language+models%2E+arXiv+preprint+arXiv%3A2207%2E00747%2E)
34. Xuezhi Wang and Denny Zhou. 2024. Chain-of-thought reasoning without prompting. arXiv preprint arXiv:2402.10200. [find](https://scholar.google.com/scholar?q=Xuezhi+Wang+and+Denny+Zhou%2E+2024%2E+Chain%2Dof%2Dthought+reasoning+without+prompting%2E+arXiv+preprint+arXiv%3A2402%2E10200%2E)
35. 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.
36. Sean Welleck, Amanda Bertsch, Matthew Finlayson, Hailey Schoelkopf, Alex Xie, Graham Neubig, Ilia Kulikov, and Zaid Harchaoui. 2024. [From decoding to meta-generation: Inference-time algorithms for large language models](https://md.research.elamur.ai/free/en/papers/welleck-2024-decoding-meta-generation-inference-time/). arXiv preprint arXiv:2406.16838.
37. Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, James Xu Zhao, Min-Yen Kan, Junxian He, and Michael Xie. 2023. [Self-evaluation guided beam search for reasoning](https://md.research.elamur.ai/free/en/papers/xie-2023-self-evaluation-guided-beam-search/). Advances in Neural Information Processing Systems, 36:41618–41650.
38. Jiaming Xu, Jiayi Pan, Yongkang Zhou, Siming Chen, Jinhao Li, Yaoxiu Lian, Junyi Wu, and Guohao Dai. 2025. Specee: Accelerating large language model inference with speculative early exiting. arXiv preprint arXiv:2504.08850. [find](https://scholar.google.com/scholar?q=Jiaming+Xu%2C+Jiayi+Pan%2C+Yongkang+Zhou%2C+Siming+Chen%2C+Jinhao+Li%2C+Yaoxiu+Lian%2C+Junyi+Wu%2C+and+Guohao+Dai%2E+2025%2E+Specee%3A+Accelerating+large+language+model+inference+with+speculative+early+exiting%2E+arXiv+pre)
39. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, and 1 others. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+and+1+others%2E+2024%2E+Qwen2%2E+5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115)
40. Liang Yao. 2024. Large language models are contrastive reasoners. arXiv preprint arXiv:2403.08211. — [arXiv:2403.08211](https://arxiv.org/abs/2403.08211) [find](https://scholar.google.com/scholar?q=Liang+Yao%2E+2024%2E+Large+language+models+are+contrastive+reasoners%2E+arXiv+preprint+arXiv%3A2403%2E08211%2E+%E2%80%94+%5BarXiv%3A2403%2E08211%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2403%2E08211%29)
41. 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. In Advances in Neural Information Processing Systems, volume 36, pages 11809–11822. Curran Associates, Inc. [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+In+Advances+in+Neural+)
42. Michihiro Yasunaga, Xinyun Chen, Yujia Li, Panupong Pasupat, Jure Leskovec, Percy Liang, Ed H Chi, and Denny Zhou. 2023. Large language models as analogical reasoners. arXiv preprint arXiv:2310.01714. [find](https://scholar.google.com/scholar?q=Michihiro+Yasunaga%2C+Xinyun+Chen%2C+Yujia+Li%2C+Panupong+Pasupat%2C+Jure+Leskovec%2C+Percy+Liang%2C+Ed+H+Chi%2C+and+Denny+Zhou%2E+2023%2E+Large+language+models+as+analogical+reasoners%2E+arXiv+preprint+arXiv%3A2310%2E01714%2E)
43. Xi Ye and Greg Durrett. 2022. [The unreliability of explanations in few-shot prompting for textual reasoning](https://md.research.elamur.ai/free/en/papers/ye-2022-unreliability-explanations-few-shot-prompting/). Advances in neural information processing systems, 35:30378–30392. *Table 9: Distribution of correct and incorrect paths and their corresponding confidences for the top 100 GSM8K questions in…
44. Yufeng Zhang, Xuepeng Wang, Lingxiang Wu, and Jinqiao Wang. 2024b. Enhancing chain of thought prompting in large language models via reasoning patterns. arXiv preprint arXiv:2404.14812. — [arXiv:2404.14812](https://arxiv.org/abs/2404.14812) [find](https://scholar.google.com/scholar?q=Yufeng+Zhang%2C+Xuepeng+Wang%2C+Lingxiang+Wu%2C+and+Jinqiao+Wang%2E+2024b%2E+Enhancing+chain+of+thought+prompting+in+large+language+models+via+reasoning+patterns%2E+arXiv+preprint+arXiv%3A2404%2E14812%2E+%E2%80%94+%5BarXiv%3A2404%2E)
45. Index Correct Incorrect C. Conf. I. Conf. 0 1 2 3 4 5 6 7 8 9 – 8 2 13 23 18 28 35 68 44 – 92 98 87 77 82 72 65 32 56 – 0.73 0.68 0.70 0.74 0.71 0.69 0.67 0.64 0.62 – 0.09 0.13 0.10 0.14 0.15 0.16 0.17 0.18 0.20 [find](https://scholar.google.com/scholar?q=Index+Correct+Incorrect+C%2E+Conf%2E+I%2E+Conf%2E+0+1+2+3+4+5+6+7+8+9+%E2%80%93+8+2+13+23+18+28+35+68+44+%E2%80%93+92+98+87+77+82+72+65+32+56+%E2%80%93+0%2E73+0%2E68+0%2E70+0%2E74+0%2E71+0%2E69+0%2E67+0%2E64+0%2E62+%E2%80%93+0%2E09+0%2E13+0%2E10+0%2E14+0%2E15+0%2E16+0%2E1)
46. Zhanke Zhou, Rong Tao, Jianing Zhu, Yiwen Luo, Zengmao Wang, and Bo Han. 2024. Can language models perform robust reasoning in chain-of-thought prompting with noisy rationales? Advances in Neural Information Processing Systems, 37:123846–123910. [find](https://scholar.google.com/scholar?q=Zhanke+Zhou%2C+Rong+Tao%2C+Jianing+Zhu%2C+Yiwen+Luo%2C+Zengmao+Wang%2C+and+Bo+Han%2E+2024%2E+Can+language+models+perform+robust+reasoning+in+chain%2Dof%2Dthought+prompting+with+noisy+rationales%3F+Advances+in+Neural+Info)

*Updated 31 October 2026*