Large Language Models Are Neurosymbolic Reasoners

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

Large Language Models Are Neurosymbolic Reasoners

Fang, M; Deng, S; Zhang, Y; Shi, Z; Chen, L; Pechenizkiy, M; Wang, J; (2024) Large Language Models Are Neurosymbolic Reasoners. In: Proceedings of the AAAI Conference on Artificial Intelligence. (pp. pp. 17985-17993). Association for the Advancement of Artificial Intelligence (AAAI) Green open access

Preview

Text
2401.09334v1.pdf - Accepted Version
Download (254kB) | Preview

Abstract

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.

Type:	Proceedings paper
Title:	Large Language Models Are Neurosymbolic Reasoners
Event:	The 38th Annual AAAI Conference on Artificial Intelligence
Open access status:	An open access version is available from UCL Discovery
DOI:	10.1609/aaai.v38i16.29754
Publisher version:	http://dx.doi.org/10.1609/aaai.v38i16.29754
Language:	English
Additional information:	This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification:	UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI:	https://discovery.ucl.ac.uk/id/eprint/10194858