<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="watanabe-kano-2024-werewolf">
    <titleInfo>
        <title>Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Neo</namePart>
        <namePart type="family">Watanabe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoshinobu</namePart>
        <namePart type="family">Kano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd International AIWolfDial Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoshinobu</namePart>
            <namePart type="family">Kano</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In recent years, AI models based on GPT have advanced rapidly. These models are capable of generating text, translating between different languages, and answering questions with high accuracy. However, the process behind their outputs remains a black box, making it difficult to ascertain the data influencing their responses. These AI models do not always produce accurate outputs and are known for generating incorrect information, known as hallucinations, whose causes are hard to pinpoint. Moreover, they still face challenges in solving complex problems that require step-by-step reasoning, despite various improvements like the Chain-of-Thought approach. There’s no guarantee that these models can independently perform logical reasoning from scratch, raising doubts about the reliability and accuracy of their inferences. To address these concerns, this study proposes the incorporation of an explicit logical structure into the AI’s text generation process. As a validation experiment, a text-based agent capable of playing the Werewolf game, which requires deductive reasoning, was developed using GPT-4. By comparing the model combined with an external explicit logical structure and a baseline that lacks such a structure, the proposed method demonstrated superior reasoning capabilities in subjective evaluations, suggesting the effectiveness of adding an explicit logical framework to the conventional AI models.</abstract>
    <identifier type="citekey">watanabe-kano-2024-werewolf</identifier>
    <location>
        <url>https://aclanthology.org/2024.aiwolfdial-1.3</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>21</start>
            <end>29</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players
%A Watanabe, Neo
%A Kano, Yoshinobu
%Y Kano, Yoshinobu
%S Proceedings of the 2nd International AIWolfDial Workshop
%D 2024
%8 September
%I Association for Computational Linguistics
%C Tokyo, Japan
%F watanabe-kano-2024-werewolf
%X In recent years, AI models based on GPT have advanced rapidly. These models are capable of generating text, translating between different languages, and answering questions with high accuracy. However, the process behind their outputs remains a black box, making it difficult to ascertain the data influencing their responses. These AI models do not always produce accurate outputs and are known for generating incorrect information, known as hallucinations, whose causes are hard to pinpoint. Moreover, they still face challenges in solving complex problems that require step-by-step reasoning, despite various improvements like the Chain-of-Thought approach. There’s no guarantee that these models can independently perform logical reasoning from scratch, raising doubts about the reliability and accuracy of their inferences. To address these concerns, this study proposes the incorporation of an explicit logical structure into the AI’s text generation process. As a validation experiment, a text-based agent capable of playing the Werewolf game, which requires deductive reasoning, was developed using GPT-4. By comparing the model combined with an external explicit logical structure and a baseline that lacks such a structure, the proposed method demonstrated superior reasoning capabilities in subjective evaluations, suggesting the effectiveness of adding an explicit logical framework to the conventional AI models.
%U https://aclanthology.org/2024.aiwolfdial-1.3
%P 21-29

Markdown (Informal)

[Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players](https://aclanthology.org/2024.aiwolfdial-1.3) (Watanabe & Kano, AIWolfDial-WS 2024)

• Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players (Watanabe & Kano, AIWolfDial-WS 2024)

ACL

• Neo Watanabe and Yoshinobu Kano. 2024. Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players. In Proceedings of the 2nd International AIWolfDial Workshop, pages 21–29, Tokyo, Japan. Association for Computational Linguistics.