@inproceedings{huang-2024-toward,
title = "Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems",
author = "Huang, Sicong",
editor = "Inoue, Koji and
Fu, Yahui and
Axelsson, Agnes and
Ohashi, Atsumoto and
Madureira, Brielen and
Zenimoto, Yuki and
Mohapatra, Biswesh and
Stricker, Armand and
Khosla, Sopan",
booktitle = "Proceedings of the 20th Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.yrrsds-1.14",
pages = "37--39",
abstract = "My primary research interests lie in evaluating and improving the faithfulness of language model-based text generation systems. Recent advances in large language models (LLMs) such as GPT-4 and Llama have enabled the wide adoption of LLMs in various aspects of natural language processing (NLP). Despite their widespread use, LLMs still suffer from the problem of hallucination, limiting the practicality of deploying such systems in use cases where being factual and faithful is of critical importance. My research specifically aims to evaluate and improve the faithfulness, i.e. the factual alignment between the generated text and a given context, of text generation systems. By developing techniques to reliably evaluate, label, and improve generation faithfulness, we can enable wider adoption of dialog systems that need to converse with human users using accurate information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-2024-toward">
<titleInfo>
<title>Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sicong</namePart>
<namePart type="family">Huang</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 20th Workshop of Young Researchers’ Roundtable on Spoken Dialogue Systems</title>
</titleInfo>
<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">Yahui</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnes</namePart>
<namePart type="family">Axelsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsumoto</namePart>
<namePart type="family">Ohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brielen</namePart>
<namePart type="family">Madureira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Zenimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biswesh</namePart>
<namePart type="family">Mohapatra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armand</namePart>
<namePart type="family">Stricker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sopan</namePart>
<namePart type="family">Khosla</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>My primary research interests lie in evaluating and improving the faithfulness of language model-based text generation systems. Recent advances in large language models (LLMs) such as GPT-4 and Llama have enabled the wide adoption of LLMs in various aspects of natural language processing (NLP). Despite their widespread use, LLMs still suffer from the problem of hallucination, limiting the practicality of deploying such systems in use cases where being factual and faithful is of critical importance. My research specifically aims to evaluate and improve the faithfulness, i.e. the factual alignment between the generated text and a given context, of text generation systems. By developing techniques to reliably evaluate, label, and improve generation faithfulness, we can enable wider adoption of dialog systems that need to converse with human users using accurate information.</abstract>
<identifier type="citekey">huang-2024-toward</identifier>
<location>
<url>https://aclanthology.org/2024.yrrsds-1.14</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>37</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems
%A Huang, Sicong
%Y Inoue, Koji
%Y Fu, Yahui
%Y Axelsson, Agnes
%Y Ohashi, Atsumoto
%Y Madureira, Brielen
%Y Zenimoto, Yuki
%Y Mohapatra, Biswesh
%Y Stricker, Armand
%Y Khosla, Sopan
%S Proceedings of the 20th Workshop of Young Researchers’ Roundtable on Spoken Dialogue Systems
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F huang-2024-toward
%X My primary research interests lie in evaluating and improving the faithfulness of language model-based text generation systems. Recent advances in large language models (LLMs) such as GPT-4 and Llama have enabled the wide adoption of LLMs in various aspects of natural language processing (NLP). Despite their widespread use, LLMs still suffer from the problem of hallucination, limiting the practicality of deploying such systems in use cases where being factual and faithful is of critical importance. My research specifically aims to evaluate and improve the faithfulness, i.e. the factual alignment between the generated text and a given context, of text generation systems. By developing techniques to reliably evaluate, label, and improve generation faithfulness, we can enable wider adoption of dialog systems that need to converse with human users using accurate information.
%U https://aclanthology.org/2024.yrrsds-1.14
%P 37-39
Markdown (Informal)
[Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems](https://aclanthology.org/2024.yrrsds-1.14) (Huang, YRRSDS-WS 2024)
ACL