探究大模型能否自主进行符号推理及其实现路径。
Can Large Language Models Act as Symbolic Reasoners?
- 分析大模型是否具备内在符号推理能力，而非依赖外部组件。
- 发现当前大模型的推理能力多限于特定任务，尚无普遍适用证据。
- 适合关注AI可解释性与推理机制的研究者阅读。
大型语言模型（LLMs）在众多领域表现卓越，但常被质疑缺乏对其推理过程和结论的解释能力，难以阐明推导逻辑或制定策略。本文综述了当前关于符号推理与大模型的研究进展，探讨大模型是否能内生地实现某种形式的推理，或必须依赖外部支持组件；若存在推理能力，该能力是特定领域的特性，还是普遍存在的通用能力？此外，本文旨在识别当前研究中的空白与未来趋势，系统回顾相关文献，梳理现有研究现状，并提出未来研究方向。
原文摘要 · Abstract (English)
The performance of Large language models (LLMs) across a broad range of domains has been impressive but have been critiqued as not being able to reason about their process and conclusions derived. This is to explain the conclusions draw, and also for determining a plan or strategy for their approach. This paper explores the current research in investigating symbolic reasoning and LLMs, and whether an LLM can inherently provide some form of reasoning or whether supporting components are necessary, and, if there is evidence for a reasoning capability, is this evident in a specific domain or is this a general capability? In addition, this paper aims to identify the current research gaps and future trends of LLM explainability, presenting a review of the literature, identifying current research into this topic and suggests areas for future work.
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。