Elamur Research
☰
home / papers / 2024 / To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Written for the Research library (claude-opus-5-5) from the paper text. Original — arxiv.org/pdf/2409.12183

Summary

Chain-of-thought (CoT) prompting, where a large language model is asked to reason step by step, is widely treated as a general booster for reasoning. Most of the supporting evidence, however, comes from math benchmarks. The authors test how far the benefit really extends, using two lines of evidence. First, they run a quantitative meta-analysis of papers from ICLR 2024, EACL 2024 and NAACL 2024 that compare CoT against direct answering. Second, they evaluate 14 recent LLMs on 20 datasets covering five reasoning categories, with both zero-shot and few-shot prompts. The two sources agree. Large gains show up almost only on math, logic and other symbolic or algorithmic tasks. Commonsense, knowledge-heavy and other "soft" tasks gain little, and sometimes accuracy drops. When the authors split symbolic problems into a planning stage and an execution stage, CoT mainly helps with carrying out the computation. Still, an LLM that writes a formal plan and passes it to an external symbolic solver does better than CoT. In practice, CoT can be used selectively to save inference cost without losing accuracy, and better ways to use intermediate computation are needed beyond simple prompting.

Key points

  • Meta-analysis: 4,642 papers were screened, leaving 110 papers with 1,218 CoT-vs-direct comparisons. The categories with the largest average gains were symbolic reasoning (+14.2), math (+12.3) and logical reasoning (+6.9).
  • MMLU / MMLU Pro: CoT helps mainly on the math portions. Up to 95% of the CoT gain on MMLU comes from items where an "=" sign appears in the question or in the model's output. For non-math questions, no feature reliably predicts when CoT will help.
  • Prompt settings: Few-shot CoT prompts perform about the same as zero-shot ones. Tasks range from symbolic (MATH) through semi-symbolic (MuSR) to non-symbolic (CommonsenseQA).
  • Planning vs. execution: CoT beats direct answering at executing formal solution plans, but an LLM-written plan run by a symbolic solver beats CoT on both stages.
  • Resources: Code is at github.com/Zayne-sprague/To-CoT-or-not-to-CoT. All prompts and model outputs for each dataset and model are released on Huggingface.

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

Fields: Natural language processing · AI & machine learning

Cited by

120 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 117 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2409.12183 · arXiv 2409.12183

@misc{sprague2024cot,
  title = {{To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning}},
  author = {Sprague, Zayne and Yin, Fangcong and Rodriguez, Juan Diego and Jiang, Dongwei and Wadhwa, Manya and Singhal, Prasann and Zhao, Xinyu and Ye, Xi and Mahowald, Kyle and Durrett, Greg},
  year = {2024},
  doi = {10.48550/arxiv.2409.12183},
  eprint = {2409.12183},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2409.12183}
}

References

106 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, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Hassan Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Singh Behl, Alon Benhaim, Misha Bilenko, Johan Bjorck, Sébastien Bubeck, Martin Cai, Caio C’esar Teodoro Mendes, Weizhu Chen, Vishrav Chaudhary, Par… find our card
  2. Anthropic. The Claude 3 Model Family: Opus, Sonnet, Haiku. a. URL https://www-cdn. anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model Card Claude 3. pdf. Anthropic. Claude 3.5 Sonnet Model Card Addendum. b. URL https://www-cdn.anthropic. com/fed9cc193a14b84131812372d8d5857f8f304c52/Model C… ↗
  3. Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, and Yejin Choi. Piqa: Reasoning about physical commonsense in natural language. In AAAI Conference on Artificial Intelligence, 2019. URL https://api.semanticscholar.org/CorpusID:208290939. ↗ our card
  4. Leonard Bongard, Lena Held, and Ivan Habernal. The legal argument reasoning task in civil procedure. In Nikolaos Aletras, Ilias Chalkidis, Leslie Barrett, Cătălina Goant , ă, and Daniel Preot , iuc-Pietro (eds.), Proceedings of the Natural Legal Language Processing Workshop 2022, pp. 194– 207, Ab… find
  5. Chen Bowen, Rune Sætre, and Yusuke Miyao. A comprehensive evaluation of inductive reasoning capabilities and problem solving in large language models. In Yvette Graham and Matthew Purver (eds.), Findings of the Association for Computational Linguistics: EACL 2024, pp. 323–339, St. find
  6. Julian’s, Malta, March 2024. Association for Computational Linguistics. URL https:// aclanthology.org/2024.findings-eacl.22. find
  7. 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… find
  8. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper files/paper/2020/file/ 1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf. ↗
  9. Hyungjoo Chae, Yeonghyeon Kim, Seungone Kim, Kai Tzu-iunn Ong, Beong-woo Kwak, Moohyeon Kim, Seonghwan Kim, Taeyoon Kwon, Jiwan Chung, Youngjae Yu, et al. Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models. arXiv preprint arXiv:2404.02575,… find
  10. Chih Yao Chen, Swarnadeep Saha, and Mohit Bansal. Reconcile: Round-table conference improves reasoning via consensus among diverse LLMs, 2024. URL https://openreview.net/forum? id=Yol6nUVIJD. ↗
  11. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W. Cohen. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. Transactions on Machine Learning Research, 2023. ISSN 2835-8856. URL https://openreview.net/forum?id= YfZ4ZPt8zd. ↗ our card
  12. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. arXiv:1803.05457v1, 2018. find
  13. 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. ArXiv, abs/2110.14168, 2021. URL https://api.semanticscholar.or… ↗ our card
  14. Marie-Catherine de Marneffe, Mandy Simons, and Judith Tonhauser. The CommitmentBank: Investigating projection in naturally occurring discourse. In Proceedings of Sinn und Bedeutung 23, 2019. find our card
  15. Leonardo De Moura and Nikolaj Bjørner. Z3: An efficient SMT solver. In Proceedings of the Theory and Practice of Software, 14th International Conference on Tools and Algorithms for the Construction and Analysis of Systems, TACAS’08/ETAPS’08, pp. 337–340, Berlin, Heidelberg, 2008. Springer-Verlag. IS… find
  16. Yuntian Deng, Yejin Choi, and Stuart Shieber. From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step. arXiv preprint arXiv:2405.14838, 2024. find
  17. Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325, 2023. find our card
  18. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. The Llama 3 Herd of Models. arXiv preprint arXiv:2407.21783, 2024. find
  19. Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback, 2023. find our card
  20. 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.… find our card
  21. Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. Complexity-based prompting for multi-step reasoning. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=yf1icZHC-l9. ↗ our card
  22. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. Pal: program-aided language models. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org, 2023. find
  23. Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. Did Aristotle use a laptop? A question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346–361, February 2021. ISSN 2307-387X. doi: 10.1162/tacl… find
  24. L. Guan, Yifan Zhou, Denis Liu, Yantian Zha, Heni Ben Amor, and Subbarao Kambhampati. ”Task Success” is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors. ArXiv, abs/2402.04210, 2024. URL https://api. semanticscholar.org/CorpusID:… — [arXiv:2402.04210](https://arxiv.org/abs/2402.04210) find
  25. Atharva Gundawar, Mudit Verma, L. Guan, Karthik Valmeekam, Siddhant Bhambri, and Subbarao Kambhampati. Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning. ArXiv, abs/2405.20625, 2024. URL https://api.semanticscholar.org/CorpusID: 270199944. — [arXiv:2405.20625](https://arxiv.org/abs/2405.20625) ↗
  26. Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Luke Benson, Lucy Sun, Ekaterina Zubova, Yujie Qiao, Matthew Burtell, David Peng, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Shafiq Joty, Alexander R. Fabbri, Woj… find our card
  27. Shibo Hao, Yi Gu, Haodi Ma, Joshua Hong, Zhen Wang, Daisy Wang, and Zhiting Hu. Reasoning with language model is planning with world model. In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 8154–8173, Sing… find
  28. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. Proceedings of the International Conference on Learning Representations (ICLR), 2021a. find our card
  29. 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. NeurIPS, 2021b. find our card
  30. Hanxu Hu, Hongyuan Lu, Huajian Zhang, Wai Lam, and Yue Zhang. Chain-of-symbol prompting elicits planning in large langauge models, 2023. find
  31. Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Shuhang Lin, Mingyu Jin, Haochen Xue, Zelong Li, Jindong Wang, and Yongfeng Zhang. Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities. ArXiv, abs/2406.02787, 2024. URL https://api. semanticscholar.org/CorpusID:27025… find
  32. Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. arXiv preprint arXiv:2201.07207, 2022. find our card
  33. Jinghan Jia, Abi Komma, Timothy Leffel, Xujun Peng, Ajay Nagesh, Tamer Soliman, Aram Galstyan, and Anoop Kumar. Leveraging LLMs for dialogue quality measurement. In Yi Yang, Aida Davani, Avi Sil, and Anoop Kumar (eds.), Proceedings of the 2024 Conference of the North American Chapter of the Associat… find
  34. Albert Qiaochu Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L’elio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée L… find
  35. Dongwei Jiang, Marcio Fonseca, and Shay B. Cohen. Leanreasoner: Boosting complex logical reasoning with lean. In Kevin Duh, Helena Gómez-Adorno, and Steven Bethard (eds.), Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua… find
  36. Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, and Xiang Ren. Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales. ArXiv, abs/2305.07095, 2023. URL https: //api.semanticscholar.org/Corpus… find
  37. Subbarao Kambhampati. Can large language models reason and plan? Annals of the New York Academy of Sciences, 1534:15 – 18, 2024. URL https://api.semanticscholar.org/ CorpusID:268249961. ↗
  38. Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri, Lucas Paul Saldyt, and Anil B Murthy. Position: LLMs can’t plan, but can help planning in LLM-modulo frameworks. In Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonath… find
  39. Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri, Lucas Paul Saldyt, and Anil B Murthy. Position: LLMs can’t plan, but can help planning in LLM-modulo frameworks. In Forty-first International Conference on Machine Learning, 2024b. URL https://openreview.… ↗
  40. Liwei Kang, Zirui Zhao, David Hsu, and Wee Sun Lee. On the empirical complexity of reasoning and planning in llms. arXiv preprint arXiv:2404.11041, 2024. find
  41. Marzena Karpinska, Katherine Thai, Kyle Lo, Tanya Goyal, and Mohit Iyyer. One thousand and one pairs: A ”novel” challenge for long-context language models. ArXiv, abs/2406.16264, 2024. URL https://api.semanticscholar.org/CorpusID:270703648. ↗
  42. Tushar Khot, H. Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sabharwal. Decomposed prompting: A modular approach for solving complex tasks. In The International Conference on Learning Representations, volume abs/2210.02406, 2023. URL https://api.semanticscholar.org/Co… ↗
  43. Seungone Kim, Juyoung Suk, Ji Yong Cho, Shayne Longpre, Chaeeun Kim, Dongkeun Yoon, Guijin Son, Yejin Cho, Sheikh Shafayat, Jinheon Baek, et al. The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models. arXiv preprint arXiv:2406.05761, 2024. find
  44. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. Large language models are zero-shot reasoners. In Proceedings of the 36th International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 2022. Curran Associates Inc. ISBN 9781713871088. find our card
  45. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles, 2023. find
  46. Brenden M. Lake and Marco Baroni. Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks. In Jennifer G. Dy and Andreas Krause (eds.), Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stock-holmsmässan, Stockholm,… find
  47. PMLR, 2018. URL http://proceedings.mlr.press/v80/ lake18a.html. ↗
  48. Tamera Lanham, Anna Chen, Ansh Radhakrishnan, Benoit Steiner, Carson Denison, Danny Hernandez, Dustin Li, Esin Durmus, Evan Hubinger, Jackson Kernion, et al. Measuring faithfulness in chain-of-thought reasoning. arXiv preprint arXiv:2307.13702, 2023. find our card
  49. Fangyu Lei, Qian Liu, Yiming Huang, Shizhu He, Jun Zhao, and Kang Liu. S3Eval: A synthetic, scalable, systematic evaluation suite for large language model. In Kevin Duh, Helena Gomez, and Steven Bethard (eds.), Proceedings of the 2024 Conference of the North American Chapter of the Association for C… find
  50. Tianwen Li, Zhexiong Liu, Lindsay Matsumura, Elaine Wang, Diane Litman, and Richard Correnti. Using large language models to assess young students’ writing revisions. In Ekaterina Kochmar, Marie Bexte, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Anaı̈s Tack, Victoria Yaneva, and Zheng Yuan… find
  51. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/ forum?id=v8L0pN6EOi. ↗ our card
  52. B. Liu, Yuqian Jiang, Xiaohan Zhang, Qian Liu, Shiqi Zhang, Joydeep Biswas, and Peter Stone. Llm+p: Empowering large language models with optimal planning proficiency. ArXiv, abs/2304.11477, 2023a. URL https://api.semanticscholar.org/CorpusID:258298051. ↗ our card
  53. Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, and Cyril Zhang. Transformers learn shortcuts to automata. In The Eleventh International Conference on Learning Representations, 2023b. URL https://openreview.net/forum?id=De4FYqjFueZ. ↗
  54. Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. Learn to explain: Multimodal reasoning via thought chains for science question answering. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (eds.)… find
  55. Yingwei Ma, Yue Liu, Yue Yu, Yuanliang Zhang, Yu Jiang, Changjian Wang, and Shanshan Li. At Which Training Stage Does Code Data Help LLMs Reasoning? In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. find
  56. OpenReview.net, 2024. URL https://openreview.net/forum?id=KIPJKST4gw. ↗
  57. Aman Madaan and Amir Yazdanbakhsh. Text and patterns: For effective chain of thought, it takes two to tango. ArXiv, abs/2209.07686, 2022. URL https://api.semanticscholar.org/ CorpusID:252355328. ↗
  58. William Merrill and Ashish Sabharwal. The expressive power of transformers with chain of thought. In The International Conference on Learning Representations, volume abs/2310.07923, 2024. URL https://api.semanticscholar.org/CorpusID:263909434. ↗
  59. 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, 2022. URL https://openreview.… ↗ our card
  60. Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, and Armando Solar-Lezama. Is self-repair a silver bullet for code generation? In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=y0GJXRungR. ↗
  61. OpenAI. GPT-4 Technical Report. ArXiv, abs/2303.08774, 2023. semanticscholar.org/CorpusID:257532815. find our card
  62. URL https://api. Liangming Pan, Alon Albalak, Xinyi Wang, and William Wang. Logic-LM: Empowering large language models with symbolic solvers for faithful logical reasoning. In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Findings of the Association for Computational Linguistics: EMNLP 2023, pp.… find our card
  63. Xiangyu Peng, Siyan Li, Sarah Wiegreffe, and Mark Riedl. Inferring the reader: Guiding automated story generation with commonsense reasoning. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (eds.), Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 7008–7029, Abu Dhabi, Un… find
  64. Zhenting Qi, Mingyuan Ma, Jiahang Xu, Li Lyna Zhang, Fan Yang, and Mao Yang. Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers. arXiv preprint arXiv:2408.06195, 2024. find
  65. Xin Quan, Marco Valentino, Louise Dennis, and Andre Freitas. Enhancing ethical explanations of large language models through iterative symbolic refinement. In Yvette Graham and Matthew Purver (eds.), Proceedings of the 18th Conference of the European Chapter of the Association for Computational Ling… find
  66. Machel Reid and et. al. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. ArXiv, abs/2403.05530, 2024. URL https://api.semanticscholar.org/ CorpusID:268297180. ↗ our card
  67. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. GPQA: A Graduate-Level Google-Proof Q&A Benchmark, 2023. find our card
  68. Gemma Team Morgane Riviere and et. al. Gemma 2: Improving open language models at a practical size. 2024. URL https://api.semanticscholar.org/CorpusID:270843326. ↗
  69. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. WinoGrande: an adversarial winograd schema challenge at scale. Commun. ACM, 64(9):99–106, aug 2021. ISSN 0001-0782. doi: 10.1145/3474381. URL https://doi.org/10.1145/3474381. ↗
  70. Maarten Sap, Hannah Rashkin, Derek Chen, Ronan Le Bras, and Yejin Choi. Social IQa: Commonsense reasoning about social interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EM… find
  71. Abulhair Saparov and He He. Language models are greedy reasoners: A systematic formal analysis of chain-of-thought. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=qFVVBzXxR2V. ↗ our card
  72. Zayne Rea Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. MuSR: Testing the limits of chain-of-thought with multistep soft reasoning. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=jenyYQzue1. ↗
  73. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, et al. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615, 2022. find our card
  74. Maja Stahl, Leon Biermann, Andreas Nehring, and Henning Wachsmuth. Exploring LLM prompting strategies for joint essay scoring and feedback generation. In Ekaterina Kochmar, Marie Bexte, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Anaı̈s Tack, Victoria Yaneva, and Zheng Yuan (eds.), Proceed… find
  75. Kaya Stechly, Karthik Valmeekam, and Subbarao Kambhampati. On the self-verification limitations of large language models on reasoning and planning tasks. ArXiv, abs/2402.08115, 2024a. URL https://api.semanticscholar.org/CorpusID:267637077. ↗
  76. Kaya Stechly, Karthik Valmeekam, and Subbarao Kambhampati. Chain of thoughtlessness? an analysis of cot in planning. 2024b. URL https://api.semanticscholar.org/CorpusID: 269626390. ↗
  77. Simeng Sun, Yang Liu, Shuohang Wang, Dan Iter, Chenguang Zhu, and Mohit Iyyer. PEARL: Prompting large language models to plan and execute actions over long documents. In Yvette Graham and Matthew Purver (eds.), Proceedings of the 18th Conference of the European Chapter of the Association for Computa… find
  78. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc Le, Ed Chi, Denny Zhou, and Jason Wei. Challenging BIG-bench tasks and whether chain-of-thought can solve them. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Findi… find our card
  79. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. CommonsenseQA: A question answering challenge targeting commonsense knowledge. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume… find
  80. Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Daniel M. Bikel, Lukas Blecher, Cristian Cantón Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Bri… find
  81. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. MuSiQue: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 2022. find
  82. Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, and Subbarao Kambhampati. On the planning abilities of large language models - a critical investigation. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. URL https://openreview.net/forum?id= X6dEqXIsEW. ↗
  83. Karthik Valmeekam, Matthew Marquez, Alberto Olmo, Sarath Sreedharan, and Subbarao Kambhampati. PlanBench: An extensible benchmark for evaluating large language models on planning and reasoning about change. In Proceedings of the 37th International Conference on Neural Information Processing Systems,… find our card
  84. Mudit Verma, Siddhant Bhambri, and Subbarao Kambhampati. Theory of mind abilities of large language models in human-robot interaction: An illusion? Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 2024. URL https://api. semanticscholar.org/CorpusID:266902529. find
  85. 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. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association for… find our card
  86. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. In Annual Meeting of the Association for Computational Linguistics, 2023b. URL https: //api.semanticscholar.org… find
  87. 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. In The Eleventh International Conference on Learning Representations, 2023c. URL https://openreview.net/forum?id… ↗ our card
  88. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, Tianle Li, Max Ku, Kai Wang, Alex Zhuang, Rongqi Fan, Xiang Yue, and Wenhu Chen. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark, 2024… find our card
  89. 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. Advances in Neural Information Processing Systems, 35:24824–24837, 2022. find our card
  90. Li Siang Wong, Gabriel Grand, Alexander K. Lew, Noah D. Goodman, Vikash K. Mansinghka, Jacob Andreas, and Joshua B. Tenenbaum. From word models to world models: Translating from natural language to the probabilistic language of thought. ArXiv, abs/2306.12672, 2023. URL https://api.semanticscholar.or… ↗
  91. Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, and Yu Su. TravelPlanner: A Benchmark for Real-World Planning with Language Agents. ArXiv, abs/2402.01622, 2024. URL https://api.semanticscholar.org/CorpusID:267406800. ↗
  92. Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, and Bryan Hooi. Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. find
  93. OpenReview.net, 2024. URL https://openreview.net/forum?id=gjeQKFxFpZ. ↗
  94. Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, and Wynne Hsu. Faithful logical reasoning via symbolic chain-of-thought. 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)… find
  95. Xiaohan Xu, Chongyang Tao, Tao Shen, Can Xu, Hongbo Xu, Guodong Long, and Jian-Guang Lou. Re-reading improves reasoning in language models, 2024b. URL https://openreview. net/forum?id=3jXCF5dNpC. find
  96. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. Large language models as optimizers. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=Bb4VGOWELI. ↗ our card
  97. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of Thoughts: Deliberate problem solving with large language models, 2023. find
  98. Xi Ye, Qiaochu Chen, Isil Dillig, and Greg Durrett. Satisfiability-aided language models using declarative prompting. In Advances in Neural Information Processing Systems, 2023. find
  99. Hugh Zhang, Jeff Da, Dean Lee, Vaughn Robinson, Catherine Wu, Will Song, Tiffany Zhao, Pranav Raja, Dylan Slack, Qin Lyu, Sean Hendryx, Russell Kaplan, Michele Lunati, and Summer Yue. A careful examination of large language model performance on grade school arithmetic. ArXiv, abs/2405.00332, 2024. U… find
  100. Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, and Denny Zhou. Take a step back: Evoking reasoning via abstraction in large language models. In The Twelfth International Conference on Learning Representations, 2024a. URL https:// openreview.net/forum?id=3bq3… find
  101. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. Judging LLM-as-a-judge with MT-bench and Chatbot Arena. In Proceedings of the 37th International Conference on Neural In… find
  102. Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, and Nan Duan. AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models, 2023. find our card
  103. Ben Zhou, Kyle Richardson, Xiaodong Yu, and Dan Roth. Learning to decompose: Hypothetical question decomposition based on comparable texts. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (eds.), Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 2223–2235… find
  104. Ben Zhou, Hongming Zhang, Sihao Chen, Dian Yu, Hongwei Wang, Baolin Peng, Dan Roth, and Dong Yu. Conceptual and unbiased reasoning in language models. ArXiv, abs/2404.00205, 2024. URL https://api.semanticscholar.org/CorpusID:268820105. — [arXiv:2404.00205](https://arxiv.org/abs/2404.00205) ↗
  105. 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. In The Eleventh International Conference on Learning Representations, 20… find our card
  106. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. Large Language Models are Human-Level Prompt Engineers. In The Eleventh International Conference on Learning Representations, 2023b. URL https://openreview.net/ forum?id=92gvk82DE-. ↗ our card