arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.09334cs.CLcs.AI
收藏

大型语言模型是神经符号推理器

Large Language Models Are Neurosymbolic Reasoners

University of Liverpool(利物浦大学);Eindhoven University of Technology(埃因霍温理工大学);University of Technology Sydney(悉尼科技大学);University College London(伦敦大学学院)

Meng Fang, Shilong Deng, Yudi Zhang, Zijing Shi, Ling Chen, Mykola Pechenizkiy, Jun Wang

AI总结:

本文提出一种LLM智能体,通过结合特定符号模块在基于文本的游戏中执行数学、地图阅读等符号任务,实验显示其平均性能达88%,验证了LLM作为神经符号推理器的有效性。

摘要:

大量现实世界应用以其符号特性为特征,这要求具备强大的符号推理能力。本文研究了将大型语言模型(LLMs)用作符号推理器的潜在应用。我们聚焦于基于文本的游戏,这些游戏是具备自然语言能力的智能体的重要基准,尤其涉及数学、地图阅读、排序以及在基于文本的世界中运用常识等符号任务。为了辅助这些智能体,我们提出了一种LLM智能体,旨在应对符号挑战并实现游戏内目标。我们首先初始化LLM智能体并告知其角色。随后,该智能体从基于文本的游戏中接收观测信息、一组有效动作以及一个特定的符号模块。基于这些输入,LLM智能体选择一个动作并与游戏环境进行交互。我们的实验结果表明,我们的方法显著增强了LLM作为自动化智能体进行符号推理的能力,并且我们的LLM智能体在涉及符号任务的基于文本的游戏中表现有效,在所有任务上取得了88%的平均性能。

英文摘要:

A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning. This paper investigates the potential application of Large Language Models (LLMs) as symbolic reasoners. We focus on text-based games, significant benchmarks for agents with natural language capabilities, particularly in symbolic tasks like math, map reading, sorting, and applying common sense in text-based worlds. To facilitate these agents, we propose an LLM agent designed to tackle symbolic challenges and achieve in-game objectives. We begin by initializing the LLM agent and informing it of its role. The agent then receives observations and a set of valid actions from the text-based games, along with a specific symbolic module. With these inputs, the LLM agent chooses an action and interacts with the game environments. Our experimental results demonstrate that our method significantly enhances the capability of LLMs as automated agents for symbolic reasoning, and our LLM agent is effective in text-based games involving symbolic tasks, achieving an average performance of 88% across all tasks.

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。

↑