Logical Reasoning in Large Language Models: A Survey
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909491027509248 |
|---|---|
| author | Liu, Hanmeng Fu, Zhizhang Ding, Mengru Ning, Ruoxi Zhang, Chaoli Liu, Xiaozhang Zhang, Yue |
| author_facet | Liu, Hanmeng Fu, Zhizhang Ding, Mengru Ning, Ruoxi Zhang, Chaoli Liu, Xiaozhang Zhang, Yue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09100 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Logical Reasoning in Large Language Models: A Survey Liu, Hanmeng Fu, Zhizhang Ding, Mengru Ning, Ruoxi Zhang, Chaoli Liu, Xiaozhang Zhang, Yue Artificial Intelligence Computation and Language 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. |
| title | Logical Reasoning in Large Language Models: A Survey |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2502.09100 |