📄 LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Paper · 2025 · Dacheng Li, Shiyi Cao, Tyler Griggs et al.

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

🎓University of California, BerkeleyBerkeley · United States243 works · 251,774 citations

🧭 Fields, topics and concepts

Cite

Cite as Dacheng Li, Shiyi Cao, Tyler Griggs, Shu Liu, Xiangxi Mo, Eric Tang, Sumanth Hegde, Kourosh Hakhamaneshi, Shishir G. Patil, Matei Zaharia, Joseph E. Gonzalez and Ion Stoica. 2025. LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!. arXiv:2502.07374.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2502.07374 · arXiv 2502.07374

@misc{li2025llms,
  title = {{LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!}},
  author = {Dacheng Li, Shiyi Cao, Tyler Griggs, Shu Liu, Xiangxi Mo, Eric Tang, Sumanth Hegde, Kourosh Hakhamaneshi, Shishir G. Patil, Matei Zaharia, Joseph E. Gonzalez and Ion Stoica},
  year = {2025},
  doi = {10.48550/arxiv.2502.07374},
  eprint = {2502.07374},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2502.07374}
}

References

33 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
2. Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., and Steinhardt, J. Measuring mathematical problem solving with the math dataset. NeurIPS, 2021c.
3. Ahn, J., Verma, R., Lou, R., Liu, D., Zhang, R., and Yin, W. Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157, 2024.
4. Hinton, G. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
5. Biderman, D., Portes, J., Ortiz, J. J. G., Paul, M., Greengard, P., Jennings, C., King, D., Havens, S., Chiley, V., Frankle, J., et al. Lora learns less and forgets less. arXiv preprint arXiv:2405.09673, 2024. find
6. Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.
7. Brown, B., Juravsky, J., Ehrlich, R., Clark, R., Le, Q. V., Ré, C., and Mirhoseini, A. Large language monkeys: Scaling inference compute with repeated sampling. arXiv preprint arXiv:2407.21787, 2024.
8. Huang, Z., Zou, H., Li, X., Liu, Y., Zheng, Y., Chern, E., Xia, S., Qin, Y., Yuan, W., and Liu, P. O1 replication journey–part 2: Surpassing o1-preview through simple distillation, big progress or bitter lesson? arXiv preprint arXiv:2411.16489, 2024.
9. Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., and Tafjord, O. Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457, 2018.
10. Jaech, A., Kalai, A., Lerer, A., Richardson, A., El-Kishky, A., Low, A., Helyar, A., Madry, A., Beutel, A., Carney, A., et al. Openai o1 system card. arXiv preprint arXiv:2412.16720, 2024.
11. Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., et al. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021.
12. Jain, N., Han, K., Gu, A., Li, W.-D., Yan, F., Zhang, T., Wang, S., Solar-Lezama, A., Sen, K., and Stoica, I. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:2403.07974, 2024.
13. Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Yang, A., Fan, A., et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024.
14. Lambert, N., Morrison, J., Pyatkin, V., Huang, S., Ivison, H., Brahman, F., Miranda, L. J. V., Liu, A., Dziri, N., Lyu, S., et al. T\\” ulu 3: Pushing frontiers in open language model post-training. arXiv preprint arXiv:2411.15124, 2024.
15. Ghosh, S., Evuru, C. K. R., Kumar, S., S, R., Aneja, D., Jin, Z., Duraiswami, R., and Manocha, D. A closer look at the limitations of instruction tuning. arXiv preprint arXiv:2402.05119, 2024. — [arXiv:2402.05119](https://arxiv.org/abs/2402.05119) find
16. Langley, P. Crafting papers on machine learning. In Langley, P. (ed.), Proceedings of the 17th International Conference on Machine Learning (ICML 2000), pp. 1207–1216, Stanford, CA, 2000. Morgan Kaufmann. find
17. Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al. Deepseek-r1: In-LI, J., Beeching, E., Tunstall, L., Lipkin, B., Soletskyi, R., Huang, S. C., Rasul, K., Yu, L., Jiang, A., Shen, Z., Qin, Z., Dong, B., Zhou, L., Fleureau, Y., Lample, G., and Polu, S… find
18. Yuan, L., Li, W., Chen, H., Cui, G., Ding, N., Zhang, K., Zhou, B., Liu, Z., and Peng, H. Free process rewards without process labels. arXiv preprint arXiv:2412.01981, 2024.
19. Zelikman, E., Wu, Y., Mu, J., and Goodman, N. Star: Bootstrapping reasoning with reasoning. Advances in Neural Information Processing Systems, 35:15476–15488, 2022.
20. Li, R., Fu, J., Zhang, B.-W., Huang, T., Sun, Z., Lyu, C., Liu, G., Jin, Z., and Li, G. Taco: Topics in algorithmic code generation dataset. arXiv preprint arXiv:2312.14852, 2023.
21. Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36: 46595–46623, 2023.
22. Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., Leike, J., Schulman, J., Sutskever, I., and Cobbe, K. Let’s verify step by step. arXiv preprint arXiv:2305.20050, 2023.
23. Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z., Feng, Z., and Ma, Y. Llamafactory: Unified efficient fine-tuning of 100+ language models. arXiv preprint arXiv:2403.13372, 2024.
24. Min, Y., Chen, Z., Jiang, J., Chen, J., Deng, J., Hu, Y., Tang, Y., Wang, J., Cheng, X., Song, H., et al. Imitate, explore, and self-improve: A reproduction report on slow-thinking reasoning systems. arXiv preprint arXiv:2412.09413, 2024.
25. Mitchell, E., Raileanu, R., Raffel, C., Levine, J., Tsvetkov, Y., and Manning, C. D. Ieval: An instruction following benchmark. arXiv preprint arXiv:2310.07724, 2023. — [arXiv:2310.07724](https://arxiv.org/abs/2310.07724) find
26. Radford, A. Improving language understanding by generative pre-training. 2018. find
27. Snell, C., Lee, J., Xu, K., and Kumar, A. Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314, 2024.
28. Team, G., Riviere, M., Pathak, S., Sessa, P. G., Hardin, C., Bhupatiraju, S., Hussenot, L., Mesnard, T., Shahriari, B., Ramé, A., et al. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118, 2024. find
29. Team, Q. Qwq: Reflect deeply on the boundaries of the unknown, 2024. find
30. Wei, J. et al. Chain-of-thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903, 2022.
31. Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., Wei, H., et al. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115, 2024. find
32. Yao, S. et al. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601, 2023. find
33. A. Short and Long CoT Response Examples Question For how many integers n does the expression s log(n 2 ) − (log n) 2 log n − 3 represent a real number, where log denotes the base 10 logarithm? Short CoT answer (1/2) find

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/li-2025-llms-easily-learn-reason-demonstrations/