arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.13095cs.CLcs.AI

增强大型语言模型的逻辑推理能力以促进法律应用

Enhancing Logical Reasoning in Large Language Models to Facilitate Legal Applications

National Institute of Informatics（信息学研究所）

Ha-Thanh Nguyen, Wachara Fungwacharakorn, Ken Satoh

备注：
ALP@JURIX2023
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出逻辑反馈强化学习（RLLF）方法以提升LLMs的逻辑推理能力，从而扩展其在法律等逻辑密集型学科中的应用，并探索该领域研究的新途径。

摘要：

语言作为传递思想的载体，使个体间的交流成为可能。区分不同概念、识别公平与不公以及理解各种法律概念的能力，从根本上依赖于逻辑推理。大型语言模型（LLMs）试图模拟人类对语言的理解和生成，但其逻辑推理能力仍然有限。本文旨在解决一个哲学问题：在保持对语言与逻辑之间复杂关系的深刻理解的同时，如何有效地向LLMs教授逻辑推理？通过加强LLMs在逻辑推理方面的能力，我们旨在扩大其在法律和其他逻辑密集型学科中的适用性。为此，我们提出了一种逻辑反馈强化学习（RLLF）方法，该方法可作为提升LLMs推理能力的潜在框架。通过RLLF和一种修订后的评估方法，我们探索了该领域研究的新途径，并有助于开发能够处理复杂法律推理任务的LLMs，同时承认语言与逻辑之间的基本联系。

英文摘要：

Language serves as a vehicle for conveying thought, enabling communication among individuals. The ability to distinguish between diverse concepts, identify fairness and injustice, and comprehend a range of legal notions fundamentally relies on logical reasoning. Large Language Models (LLMs) attempt to emulate human language understanding and generation, but their competency in logical reasoning remains limited. This paper seeks to address the philosophical question: How can we effectively teach logical reasoning to LLMs while maintaining a deep understanding of the intricate relationship between language and logic? By focusing on bolstering LLMs' capabilities in logical reasoning, we aim to expand their applicability in law and other logic-intensive disciplines. To this end, we propose a Reinforcement Learning from Logical Feedback (RLLF) approach, which serves as a potential framework for refining LLMs' reasoning capacities. Through RLLF and a revised evaluation methodology, we explore new avenues for research in this domain and contribute to the development of LLMs capable of handling complex legal reasoning tasks while acknowledging the fundamental connection between language and logic.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑