<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hudecek-dusek-2023-large">
    <titleInfo>
        <title>Are Large Language Models All You Need for Task-Oriented Dialogue?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vojtěch</namePart>
        <namePart type="family">Hudeček</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Dusek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Svetlana</namePart>
            <namePart type="family">Stoyanchev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shafiq</namePart>
            <namePart type="family">Joty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Schlangen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ondrej</namePart>
            <namePart type="family">Dusek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Casey</namePart>
            <namePart type="family">Kennington</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Malihe</namePart>
            <namePart type="family">Alikhani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Prague, Czechia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Instruction-finetuned large language models (LLMs) gained a huge popularity recently, thanks to their ability to interact with users through conversation. In this work, we aim to evaluate their ability to complete multi-turn tasks and interact with external databases in the context of established task-oriented dialogue benchmarks. We show that in explicit belief state tracking, LLMs underperform compared to specialized task-specific models. Nevertheless, they show some ability to guide the dialogue to a successful ending through their generated responses if they are provided with correct slot values. Furthermore, this ability improves with few-shot in-domain examples.</abstract>
    <identifier type="citekey">hudecek-dusek-2023-large</identifier>
    <identifier type="doi">10.18653/v1/2023.sigdial-1.21</identifier>
    <location>
        <url>https://aclanthology.org/2023.sigdial-1.21</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>216</start>
            <end>228</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Are Large Language Models All You Need for Task-Oriented Dialogue?
%A Hudeček, Vojtěch
%A Dusek, Ondrej
%Y Stoyanchev, Svetlana
%Y Joty, Shafiq
%Y Schlangen, David
%Y Dusek, Ondrej
%Y Kennington, Casey
%Y Alikhani, Malihe
%S Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F hudecek-dusek-2023-large
%X Instruction-finetuned large language models (LLMs) gained a huge popularity recently, thanks to their ability to interact with users through conversation. In this work, we aim to evaluate their ability to complete multi-turn tasks and interact with external databases in the context of established task-oriented dialogue benchmarks. We show that in explicit belief state tracking, LLMs underperform compared to specialized task-specific models. Nevertheless, they show some ability to guide the dialogue to a successful ending through their generated responses if they are provided with correct slot values. Furthermore, this ability improves with few-shot in-domain examples.
%R 10.18653/v1/2023.sigdial-1.21
%U https://aclanthology.org/2023.sigdial-1.21
%U https://doi.org/10.18653/v1/2023.sigdial-1.21
%P 216-228

Markdown (Informal)

[Are Large Language Models All You Need for Task-Oriented Dialogue?](https://aclanthology.org/2023.sigdial-1.21) (Hudeček & Dusek, SIGDIAL 2023)

• Are Large Language Models All You Need for Task-Oriented Dialogue? (Hudeček & Dusek, SIGDIAL 2023)

ACL

• Vojtěch Hudeček and Ondrej Dusek. 2023. Are Large Language Models All You Need for Task-Oriented Dialogue?. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 216–228, Prague, Czechia. Association for Computational Linguistics.