Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies
This work addresses dialogue system limitations for AI researchers, though it is incremental as it applies existing methods to a specific game domain.
The paper tackled the challenge of enhancing dialogue generation in the Werewolf Game by developing an LLM-based AI that uses situation analysis and persuasion strategies, resulting in improved performance in complex interactive environments.
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.