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

Zhiyang Qi, Michimasa Inaba


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.
Anthology ID:
2024.aiwolfdial-1.4
Volume:
Proceedings of the 2nd International AIWolfDial Workshop
Month:
September
Year:
2024
Address:
Tokyo, Japan
Editor:
Yoshinobu Kano
Venues:
AIWolfDial | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
30–39
Language:
URL:
https://aclanthology.org/2024.aiwolfdial-1.4
DOI:
Bibkey:
Cite (ACL):
Zhiyang Qi and Michimasa Inaba. 2024. Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies. In Proceedings of the 2nd International AIWolfDial Workshop, pages 30–39, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies (Qi & Inaba, AIWolfDial-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.aiwolfdial-1.4.pdf