<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2023-prompt">
    <titleInfo>
        <title>Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maximillian</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhou</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often require abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act as a policy prior, value function, user simulator, and system model during the tree search. We evaluate GDP-Zero on the goal-oriented task PersuasionForGood, and find that its responses are preferred over ChatGPT up to 59.32% of the time, and are rated more persuasive than ChatGPT during interactive evaluations.</abstract>
    <identifier type="citekey">yu-etal-2023-prompt</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.439</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.439</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>7101</start>
            <end>7125</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning
%A Yu, Xiao
%A Chen, Maximillian
%A Yu, Zhou
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F yu-etal-2023-prompt
%X Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often require abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act as a policy prior, value function, user simulator, and system model during the tree search. We evaluate GDP-Zero on the goal-oriented task PersuasionForGood, and find that its responses are preferred over ChatGPT up to 59.32% of the time, and are rated more persuasive than ChatGPT during interactive evaluations.
%R 10.18653/v1/2023.emnlp-main.439
%U https://aclanthology.org/2023.emnlp-main.439
%U https://doi.org/10.18653/v1/2023.emnlp-main.439
%P 7101-7125

Markdown (Informal)

[Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning](https://aclanthology.org/2023.emnlp-main.439) (Yu et al., EMNLP 2023)

• Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning (Yu et al., EMNLP 2023)

ACL

• Xiao Yu, Maximillian Chen, and Zhou Yu. 2023. Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7101–7125, Singapore. Association for Computational Linguistics.