Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mensfelt, Agnieszka, Stathis, Kostas, Trencsenyi, Vince
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.12300
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916434592923648
author Mensfelt, Agnieszka
Stathis, Kostas
Trencsenyi, Vince
author_facet Mensfelt, Agnieszka
Stathis, Kostas
Trencsenyi, Vince
contents Game theory is a powerful framework for reasoning about strategic interactions, with applications in domains ranging from day-to-day life to international politics. However, applying formal reasoning tools in such contexts is challenging, as these scenarios are often expressed in natural language. To address this, we introduce a framework for the autoformalization of game-theoretic scenarios, which translates natural language descriptions into formal logic representations suitable for formal solvers. Our approach utilizes one-shot prompting and a solver that provides feedback on syntactic correctness to allow LLMs to refine the code. We evaluate the framework using GPT-4o and a dataset of natural language problem descriptions, achieving 98% syntactic correctness and 88% semantic correctness. These results show the potential of LLMs to bridge the gap between real-life strategic interactions and formal reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12300
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autoformalization of Game Descriptions using Large Language Models
Mensfelt, Agnieszka
Stathis, Kostas
Trencsenyi, Vince
Artificial Intelligence
Computer Science and Game Theory
Game theory is a powerful framework for reasoning about strategic interactions, with applications in domains ranging from day-to-day life to international politics. However, applying formal reasoning tools in such contexts is challenging, as these scenarios are often expressed in natural language. To address this, we introduce a framework for the autoformalization of game-theoretic scenarios, which translates natural language descriptions into formal logic representations suitable for formal solvers. Our approach utilizes one-shot prompting and a solver that provides feedback on syntactic correctness to allow LLMs to refine the code. We evaluate the framework using GPT-4o and a dataset of natural language problem descriptions, achieving 98% syntactic correctness and 88% semantic correctness. These results show the potential of LLMs to bridge the gap between real-life strategic interactions and formal reasoning.
title Autoformalization of Game Descriptions using Large Language Models
topic Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2409.12300