Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies

TL;DR

This paper presents a novel LLM-based AI for the Werewolf Game that leverages situation analysis and persuasion strategies to improve dialogue quality and strategic interaction in complex, incomplete information environments.

Contribution

It introduces a new approach combining situation analysis and persuasion strategies within an LLM framework for Werewolf game AI, addressing dialogue management and strategic persuasion.

Findings

Enhanced dialogue coherence in complex scenarios

Effective persuasion strategies for werewolf role

Improved AI performance in incomplete information settings

Abstract

Recent advancements in natural language processing, particularly with large language models (LLMs) like GPT-4, have significantly enhanced dialogue systems, enabling them to generate more natural and fluent conversations. Despite these improvements, challenges persist, such as managing continuous dialogues, memory retention, and minimizing hallucinations. The AIWolfDial2024 addresses these challenges by employing the Werewolf Game, an incomplete information game, to test the capabilities of LLMs in complex interactive environments. This paper introduces a LLM-based Werewolf Game AI, where each role is supported by situation analysis to aid response generation. Additionally, for the werewolf role, various persuasion strategies, including logical appeal, credibility appeal, and emotional appeal, are employed to effectively persuade other players to align with its actions.