English

Large Language Model for Science: A Study on P vs. NP

Computation and Language 2023-09-13 v1 Artificial Intelligence

Abstract

In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous reasoning throughout 97 dialogue turns, concluding "P \neq NP", which is in alignment with (Xu and Zhou, 2023). The investigation uncovers novel insights within the extensive solution space of LLMs, shedding light on LLM for Science.

Keywords

Cite

@article{arxiv.2309.05689,
  title  = {Large Language Model for Science: A Study on P vs. NP},
  author = {Qingxiu Dong and Li Dong and Ke Xu and Guangyan Zhou and Yaru Hao and Zhifang Sui and Furu Wei},
  journal= {arXiv preprint arXiv:2309.05689},
  year   = {2023}
}

Comments

73 pages

R2 v1 2026-06-28T12:18:26.797Z