融合符号与神经网络，提升大模型推理能力
Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
- 从符号→大模型、大模型→符号、双向融合三方面改进推理
- 系统梳理了神经符号方法在大模型推理中的进展
- 适合关注AI推理机制与AGI发展的研究者参考
大语言模型在多个任务中表现优异，但其推理能力仍是核心挑战。实现强推理能力被视为迈向通用人工智能的关键一步，受到学术界和产业界广泛关注。为增强大模型的推理能力，多种技术被探索，其中神经符号方法尤为有前景。本文全面综述了近期提升大模型推理能力的神经符号方法。首先形式化了推理任务，并简要介绍神经符号学习范式；随后从符号→大模型、大模型→符号、大模型+符号三个角度讨论相关方法；最后探讨关键挑战与未来方向。我们还发布了包含相关论文与资源的GitHub仓库：https://github.com/LAMDASZ-ML/Awesome-LLM-Reasoning-with-NeSy。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown promising results across various tasks, yet their reasoning capabilities remain a fundamental challenge. Developing AI systems with strong reasoning capabilities is regarded as a crucial milestone in the pursuit of Artificial General Intelligence (AGI) and has garnered considerable attention from both academia and industry. Various techniques have been explored to enhance the reasoning capabilities of LLMs, with neuro-symbolic approaches being a particularly promising way. This paper comprehensively reviews recent developments in neuro-symbolic approaches for enhancing LLM reasoning. We first present a formalization of reasoning tasks and give a brief introduction to the neurosymbolic learning paradigm. Then, we discuss neuro-symbolic methods for improving the reasoning capabilities of LLMs from three perspectives: Symbolic->LLM, LLM->Symbolic, and LLM+Symbolic. Finally, we discuss several key challenges and promising future directions. We have also released a GitHub repository including papers and resources related to this survey: https://github.com/LAMDASZ-ML/Awesome-LLM-Reasoning-with-NeSy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。