@inproceedings{stricker-paroubek-2024-shot,
title = "A Few-shot Approach to Task-oriented Dialogue Enhanced with Chitchat",
author = "Stricker, Armand and
Paroubek, Patrick",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.50",
pages = "590--602",
abstract = "Large language models (LLMs) tuned for chat have recently been adopted for few-shot end-to-end task-oriented dialogue (TOD), with some success. To further assess this method, we conduct experiments on two, more complex, task-oriented benchmarks that integrate elements of chitchat into the conversation. We enhance a few-shot baseline by adding zero-shot chitchat detection and implementing \textit{function calling} for dialogue state tracking (DST). We focus on this step in the task-oriented pipeline as it comes first, and errors due to added chitchat at this stage have the most impact on end-to-end performance. We find that this prompting method shows increased resilience to mixed-mode inputs and our enhanced pipeline allows for natural inter-mode conversations, as assessed through human evaluation. Our findings also suggest that the performance gap between few-shot prompting for TOD and supervised task-specific models is narrowing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stricker-paroubek-2024-shot">
<titleInfo>
<title>A Few-shot Approach to Task-oriented Dialogue Enhanced with Chitchat</title>
</titleInfo>
<name type="personal">
<namePart type="given">Armand</namePart>
<namePart type="family">Stricker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Paroubek</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>Large language models (LLMs) tuned for chat have recently been adopted for few-shot end-to-end task-oriented dialogue (TOD), with some success. To further assess this method, we conduct experiments on two, more complex, task-oriented benchmarks that integrate elements of chitchat into the conversation. We enhance a few-shot baseline by adding zero-shot chitchat detection and implementing function calling for dialogue state tracking (DST). We focus on this step in the task-oriented pipeline as it comes first, and errors due to added chitchat at this stage have the most impact on end-to-end performance. We find that this prompting method shows increased resilience to mixed-mode inputs and our enhanced pipeline allows for natural inter-mode conversations, as assessed through human evaluation. Our findings also suggest that the performance gap between few-shot prompting for TOD and supervised task-specific models is narrowing.</abstract>
<identifier type="citekey">stricker-paroubek-2024-shot</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.50</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>590</start>
<end>602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Few-shot Approach to Task-oriented Dialogue Enhanced with Chitchat
%A Stricker, Armand
%A Paroubek, Patrick
%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 stricker-paroubek-2024-shot
%X Large language models (LLMs) tuned for chat have recently been adopted for few-shot end-to-end task-oriented dialogue (TOD), with some success. To further assess this method, we conduct experiments on two, more complex, task-oriented benchmarks that integrate elements of chitchat into the conversation. We enhance a few-shot baseline by adding zero-shot chitchat detection and implementing function calling for dialogue state tracking (DST). We focus on this step in the task-oriented pipeline as it comes first, and errors due to added chitchat at this stage have the most impact on end-to-end performance. We find that this prompting method shows increased resilience to mixed-mode inputs and our enhanced pipeline allows for natural inter-mode conversations, as assessed through human evaluation. Our findings also suggest that the performance gap between few-shot prompting for TOD and supervised task-specific models is narrowing.
%U https://aclanthology.org/2024.sigdial-1.50
%P 590-602
Markdown (Informal)
[A Few-shot Approach to Task-oriented Dialogue Enhanced with Chitchat](https://aclanthology.org/2024.sigdial-1.50) (Stricker & Paroubek, SIGDIAL 2024)
ACL