@inproceedings{lee-etal-2024-ask,
title = "Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in {LLM}s with Metric-Guided Feedback Learning",
author = "Lee, Dongyub and
Park, Eunhwan and
Lee, Hodong and
Lim, Heuiseok",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.149",
pages = "2422--2433",
abstract = "Recent advancements in Large Language Models (LLMs) have heralded unprecedented capabilities in information-seeking and text generation, as evidenced by applications like Bing Chat and perplexity.ai. Despite these strides, challenges on hallucination and factual inconsistency continue to impede their wider real-world adoption. Contemporary methods, including retrieval-augmented LLMs and feedback-based learning, serve as alternatives to mitigate these challenges. However, challenges remain, particularly regarding referencing erroneous evidence (citation errors) and generating information not present in the evidence (hallucination). In this paper, we introduce the $\mathsf{A}^2\mathsf{R}$ framework: \textbf{A}sk, \textbf{A}ssess, and \textbf{R}efine. Our approach utilizes an \textit{explicit} evaluation paradigm, incorporating metrics specifically tailored to assess citation errors and hallucination, aiming to address these prevalent challenges robustly. Capitalizing on these evaluations, we devise a strategy to formulate actionable natural language feedback, enabling iterative refinements that yield improved factual consistency and reduced hallucinations in responses. Our experiments on ASQA, ELI5, and QAMPARI datasets demonstrate our method{'}s superiority in enhancing correctness, fluency, and citation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-ask">
<titleInfo>
<title>Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongyub</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunhwan</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hodong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in Large Language Models (LLMs) have heralded unprecedented capabilities in information-seeking and text generation, as evidenced by applications like Bing Chat and perplexity.ai. Despite these strides, challenges on hallucination and factual inconsistency continue to impede their wider real-world adoption. Contemporary methods, including retrieval-augmented LLMs and feedback-based learning, serve as alternatives to mitigate these challenges. However, challenges remain, particularly regarding referencing erroneous evidence (citation errors) and generating information not present in the evidence (hallucination). In this paper, we introduce the \mathsfA²\mathsfR framework: Ask, Assess, and Refine. Our approach utilizes an explicit evaluation paradigm, incorporating metrics specifically tailored to assess citation errors and hallucination, aiming to address these prevalent challenges robustly. Capitalizing on these evaluations, we devise a strategy to formulate actionable natural language feedback, enabling iterative refinements that yield improved factual consistency and reduced hallucinations in responses. Our experiments on ASQA, ELI5, and QAMPARI datasets demonstrate our method’s superiority in enhancing correctness, fluency, and citation quality.</abstract>
<identifier type="citekey">lee-etal-2024-ask</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.149</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>2422</start>
<end>2433</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning
%A Lee, Dongyub
%A Park, Eunhwan
%A Lee, Hodong
%A Lim, Heuiseok
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F lee-etal-2024-ask
%X Recent advancements in Large Language Models (LLMs) have heralded unprecedented capabilities in information-seeking and text generation, as evidenced by applications like Bing Chat and perplexity.ai. Despite these strides, challenges on hallucination and factual inconsistency continue to impede their wider real-world adoption. Contemporary methods, including retrieval-augmented LLMs and feedback-based learning, serve as alternatives to mitigate these challenges. However, challenges remain, particularly regarding referencing erroneous evidence (citation errors) and generating information not present in the evidence (hallucination). In this paper, we introduce the \mathsfA²\mathsfR framework: Ask, Assess, and Refine. Our approach utilizes an explicit evaluation paradigm, incorporating metrics specifically tailored to assess citation errors and hallucination, aiming to address these prevalent challenges robustly. Capitalizing on these evaluations, we devise a strategy to formulate actionable natural language feedback, enabling iterative refinements that yield improved factual consistency and reduced hallucinations in responses. Our experiments on ASQA, ELI5, and QAMPARI datasets demonstrate our method’s superiority in enhancing correctness, fluency, and citation quality.
%U https://aclanthology.org/2024.eacl-long.149
%P 2422-2433
Markdown (Informal)
[Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning](https://aclanthology.org/2024.eacl-long.149) (Lee et al., EACL 2024)
ACL