Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

Yoshiki Tanaka, Takumasa Kaneko, Hiroki Onozeki, Natsumi Ezure, Ryuichi Uehara, Zhiyang Qi, Tomoya Higuchi, Ryutaro Asahara, Michimasa Inaba

TL;DR

This study aims to enhance the consistency of the agent’s utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples to demonstrate that the agent’s utterances are contextually consistent and that the character, including tone, is maintained throughout the game.

Abstract

The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG. In recent years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game.

Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

TL;DR

This study aims to enhance the consistency of the agent’s utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples to demonstrate that the agent’s utterances are contextually consistent and that the character, including tone, is maintained throughout the game.

Abstract

The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG. In recent years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game.
Paper Structure (16 sections, 5 figures, 2 tables)

This paper contains 16 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. AI for the Werewolf Game
  4. Dialogue Summarization
  5. Persona Dialogue System
  6. Task Overview
  7. Player Roles
  8. Game Procedure
  9. Evaluation
  10. Methodology
  11. Overview
  12. Efficient Use of LLMs through Dialogue Summarization
  13. Persona Design for Coherent Utterances
  14. Action Decision via Chain-of-Thought
  15. Case Study
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Example of dialogue sampled from the self-match game log. The agents speak in a random order during each turn. In the red-highlighted part, Agent[01], the seer, denies the previous day's claim by Agent[05], the possessed, that they are the seer.
  • Figure 2: Prompt example for werewolf's response generation.
  • Figure 3: Prompt template for dialogue summarization. "[HISTORY]" is a placeholder for the dialogue history from the current day."
  • Figure 4: Prompt template for determining voting targets and an example of the LLM's output. "[HISTORY]" is a placeholder for the dialogue history, and "[CANDIDATE]" is a placeholder for the list of candidate agents to vote for.
  • Figure 5: Example of the self-match game log. The conversation on Day 0 and the agent's command "Over" indicating the end of the day's utterances are omitted.