<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wagner-ultes-2024-controllability">
    <titleInfo>
        <title>On the Controllability of Large Language Models for Dialogue Interaction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nicolas</namePart>
        <namePart type="family">Wagner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Ultes</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 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Tatsuya</namePart>
            <namePart type="family">Kawahara</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stefan</namePart>
            <namePart type="family">Ultes</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Koji</namePart>
            <namePart type="family">Inoue</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shikib</namePart>
            <namePart type="family">Mehri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Howcroft</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kazunori</namePart>
            <namePart type="family">Komatani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Kyoto, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper investigates the enhancement of Dialogue Systems by integrating the creative capabilities of Large Language Models. While traditional Dialogue Systems focus on understanding user input and selecting appropriate system actions, Language Models excel at generating natural language text based on prompts. Therefore, we propose to improve controllability and coherence of interactions by guiding a Language Model with control signals that enable explicit control over the system behaviour. To address this, we tested and evaluated our concept in 815 conversations with over 3600 dialogue exchanges on a dataset. Our experiment examined the quality of generated system responses using two strategies: An unguided strategy where task data was provided to the models, and a controlled strategy in which a simulated Dialogue Controller provided appropriate system actions. The results show that the average BLEU score and the classification of dialogue acts improved in the controlled Natural Language Generation.</abstract>
    <identifier type="citekey">wagner-ultes-2024-controllability</identifier>
    <identifier type="doi">10.18653/v1/2024.sigdial-1.19</identifier>
    <location>
        <url>https://aclanthology.org/2024.sigdial-1.19</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>216</start>
            <end>221</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the Controllability of Large Language Models for Dialogue Interaction
%A Wagner, Nicolas
%A Ultes, Stefan
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F wagner-ultes-2024-controllability
%X This paper investigates the enhancement of Dialogue Systems by integrating the creative capabilities of Large Language Models. While traditional Dialogue Systems focus on understanding user input and selecting appropriate system actions, Language Models excel at generating natural language text based on prompts. Therefore, we propose to improve controllability and coherence of interactions by guiding a Language Model with control signals that enable explicit control over the system behaviour. To address this, we tested and evaluated our concept in 815 conversations with over 3600 dialogue exchanges on a dataset. Our experiment examined the quality of generated system responses using two strategies: An unguided strategy where task data was provided to the models, and a controlled strategy in which a simulated Dialogue Controller provided appropriate system actions. The results show that the average BLEU score and the classification of dialogue acts improved in the controlled Natural Language Generation.
%R 10.18653/v1/2024.sigdial-1.19
%U https://aclanthology.org/2024.sigdial-1.19
%U https://doi.org/10.18653/v1/2024.sigdial-1.19
%P 216-221

Markdown (Informal)

[On the Controllability of Large Language Models for Dialogue Interaction](https://aclanthology.org/2024.sigdial-1.19) (Wagner & Ultes, SIGDIAL 2024)

• On the Controllability of Large Language Models for Dialogue Interaction (Wagner & Ultes, SIGDIAL 2024)

ACL

• Nicolas Wagner and Stefan Ultes. 2024. On the Controllability of Large Language Models for Dialogue Interaction. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 216–221, Kyoto, Japan. Association for Computational Linguistics.