@inproceedings{ghaddar-etal-2024-charp,
title = "{CHARP}: Conversation History {A}wa{R}eness Probing for Knowledge-grounded Dialogue Systems",
author = "Ghaddar, Abbas and
Alfonso-Hermelo, David and
Langlais, Philippe and
Rezagholizadeh, Mehdi and
Chen, Boxing and
Parthasarathi, Prasanna",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.90/",
doi = "10.18653/v1/2024.findings-acl.90",
pages = "1534--1551",
abstract = "In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a testbed, designed for evaluating supposedly non-hallucinatory models trained on the FaithDial dataset. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. Data, models, and source code will be publicly available upon acceptance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghaddar-etal-2024-charp">
<titleInfo>
<title>CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abbas</namePart>
<namePart type="family">Ghaddar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfonso-Hermelo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehdi</namePart>
<namePart type="family">Rezagholizadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="family">Parthasarathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a testbed, designed for evaluating supposedly non-hallucinatory models trained on the FaithDial dataset. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. Data, models, and source code will be publicly available upon acceptance.</abstract>
<identifier type="citekey">ghaddar-etal-2024-charp</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.90</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.90/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1534</start>
<end>1551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
%A Ghaddar, Abbas
%A Alfonso-Hermelo, David
%A Langlais, Philippe
%A Rezagholizadeh, Mehdi
%A Chen, Boxing
%A Parthasarathi, Prasanna
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F ghaddar-etal-2024-charp
%X In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a testbed, designed for evaluating supposedly non-hallucinatory models trained on the FaithDial dataset. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. Data, models, and source code will be publicly available upon acceptance.
%R 10.18653/v1/2024.findings-acl.90
%U https://aclanthology.org/2024.findings-acl.90/
%U https://doi.org/10.18653/v1/2024.findings-acl.90
%P 1534-1551
Markdown (Informal)
[CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems](https://aclanthology.org/2024.findings-acl.90/) (Ghaddar et al., Findings 2024)
ACL