大型語言模型中的邏輯推理：一項調查

Logical Reasoning in Large Language Models: A Survey

February 13, 2025

作者: Hanmeng Liu, Zhizhang Fu, Mengru Ding, Ruoxi Ning, Chaoli Zhang, Xiaozhang Liu, Yue Zhang

cs.AI

摘要

隨著像 OpenAI o3 和 DeepSeek-R1 這樣的先進推理模型的出現，大型語言模型（LLMs）展示了卓越的推理能力。然而，它們執行嚴謹邏輯推理的能力仍是一個未解之謎。本調查綜合了LLMs內邏輯推理的最新進展，這是人工智慧研究中一個關鍵領域。它概述了LLMs中邏輯推理的範圍、其理論基礎以及用於評估推理能力的基準。我們分析了不同推理範式（演繹、歸納、演繹性和類比性）之間現有的能力，並評估了增強推理表現的策略，包括以數據為中心的調整、強化學習、解碼策略和神經符號方法。評論最後提出了未來的方向，強調了需要進一步探索以加強人工智慧系統中的邏輯推理。

English

With the emergence of advanced reasoning models like OpenAI o3 and DeepSeek-R1, large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, their ability to perform rigorous logical reasoning remains an open question. This survey synthesizes recent advancements in logical reasoning within LLMs, a critical area of AI research. It outlines the scope of logical reasoning in LLMs, its theoretical foundations, and the benchmarks used to evaluate reasoning proficiency. We analyze existing capabilities across different reasoning paradigms - deductive, inductive, abductive, and analogical - and assess strategies to enhance reasoning performance, including data-centric tuning, reinforcement learning, decoding strategies, and neuro-symbolic approaches. The review concludes with future directions, emphasizing the need for further exploration to strengthen logical reasoning in AI systems.