@inproceedings{chiang-lee-2024-merging,
title = "Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations",
author = "Chiang, Cheng-Han and
Lee, Hung-yi",
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 and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.160",
pages = "2734--2751",
abstract = "Long-form generations from large language models (LLMs) contain a mix of factual and non-factual claims, making evaluating factuality difficult.Prior works evaluate the factuality of a long paragraph by decomposing it into multiple facts, verifying those facts independently, and aggregating the results.Such methods assume that combining factual claims forms a factual paragraph.The above assumption can be violated: we show that strong open-source models like Llama-chat can generate paragraphs that contain verifiable facts, but the facts are combined into a non-factual paragraph due to entity ambiguity.We further reveal that existing factuality metrics, including FActScore and citation recall, cannot properly evaluate these non-factual paragraphs and overestimate their factuality.To address this, we introduce an enhanced metric, **D-FActScore**, specifically designed for content with ambiguous entities.We evaluate the D-FActScores of people biographies generated by retrieval-augmented LLMs.We show that D-FActScore can better assess the factuality of paragraphs with entity ambiguity than FActScore.We also find that four widely used open-source LLMs tend to mix information of distinct entities to form non-factual paragraphs, making their D-FActScore much lower than FActScore by over 10{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiang-lee-2024-merging">
<titleInfo>
<title>Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng-Han</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long-form generations from large language models (LLMs) contain a mix of factual and non-factual claims, making evaluating factuality difficult.Prior works evaluate the factuality of a long paragraph by decomposing it into multiple facts, verifying those facts independently, and aggregating the results.Such methods assume that combining factual claims forms a factual paragraph.The above assumption can be violated: we show that strong open-source models like Llama-chat can generate paragraphs that contain verifiable facts, but the facts are combined into a non-factual paragraph due to entity ambiguity.We further reveal that existing factuality metrics, including FActScore and citation recall, cannot properly evaluate these non-factual paragraphs and overestimate their factuality.To address this, we introduce an enhanced metric, **D-FActScore**, specifically designed for content with ambiguous entities.We evaluate the D-FActScores of people biographies generated by retrieval-augmented LLMs.We show that D-FActScore can better assess the factuality of paragraphs with entity ambiguity than FActScore.We also find that four widely used open-source LLMs tend to mix information of distinct entities to form non-factual paragraphs, making their D-FActScore much lower than FActScore by over 10%.</abstract>
<identifier type="citekey">chiang-lee-2024-merging</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.160</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2734</start>
<end>2751</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations
%A Chiang, Cheng-Han
%A Lee, Hung-yi
%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 and virtual meeting
%F chiang-lee-2024-merging
%X Long-form generations from large language models (LLMs) contain a mix of factual and non-factual claims, making evaluating factuality difficult.Prior works evaluate the factuality of a long paragraph by decomposing it into multiple facts, verifying those facts independently, and aggregating the results.Such methods assume that combining factual claims forms a factual paragraph.The above assumption can be violated: we show that strong open-source models like Llama-chat can generate paragraphs that contain verifiable facts, but the facts are combined into a non-factual paragraph due to entity ambiguity.We further reveal that existing factuality metrics, including FActScore and citation recall, cannot properly evaluate these non-factual paragraphs and overestimate their factuality.To address this, we introduce an enhanced metric, **D-FActScore**, specifically designed for content with ambiguous entities.We evaluate the D-FActScores of people biographies generated by retrieval-augmented LLMs.We show that D-FActScore can better assess the factuality of paragraphs with entity ambiguity than FActScore.We also find that four widely used open-source LLMs tend to mix information of distinct entities to form non-factual paragraphs, making their D-FActScore much lower than FActScore by over 10%.
%U https://aclanthology.org/2024.findings-acl.160
%P 2734-2751
Markdown (Informal)
[Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations](https://aclanthology.org/2024.findings-acl.160) (Chiang & Lee, Findings 2024)
ACL