@inproceedings{iqbal-etal-2024-openfactcheck,
title = "{O}pen{F}act{C}heck: A Unified Framework for Factuality Evaluation of {LLM}s",
author = "Iqbal, Hasan and
Wang, Yuxia and
Wang, Minghan and
Georgiev, Georgi Nenkov and
Geng, Jiahui and
Gurevych, Iryna and
Nakov, Preslav",
editor = "Hernandez Farias, Delia Irazu and
Hope, Tom and
Li, Manling",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-demo.23",
pages = "219--229",
abstract = "The increased use of large language models (LLMs) across a variety of real-world applications calls for automatic tools to check the factual accuracy of their outputs, as LLMs often hallucinate. This is difficult as it requires assessing the factuality of free-form open-domain responses. While there has been a lot of research on this topic, different papers use different evaluation benchmarks and measures,which makes them hard to compare and hampers future progress. To mitigate these issues, we developed OpenFactCheck, a unified framework, with three modules: (i) RESPONSEEVAL, which allows users to easily customize an automatic fact-checking system and to assess the factuality of all claims in an input document using that system, (ii) LLMEVAL, which assesses the overall factuality of an LLM, and (iii) CHECKEREVAL, a module to evaluate automatic fact-checking systems. OpenFactCheck is open-sourced (https://github.com/mbzuai-nlp/openfactcheck) and publicly released as a Python library (https://pypi.org/project/openfactcheck/) and also as a web service (http://app.openfactcheck.com). A video describing the system is available at https://youtu.be/-i9VKL0HleI.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iqbal-etal-2024-openfactcheck">
<titleInfo>
<title>OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Iqbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgi</namePart>
<namePart type="given">Nenkov</namePart>
<namePart type="family">Georgiev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahui</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Delia</namePart>
<namePart type="given">Irazu</namePart>
<namePart type="family">Hernandez Farias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increased use of large language models (LLMs) across a variety of real-world applications calls for automatic tools to check the factual accuracy of their outputs, as LLMs often hallucinate. This is difficult as it requires assessing the factuality of free-form open-domain responses. While there has been a lot of research on this topic, different papers use different evaluation benchmarks and measures,which makes them hard to compare and hampers future progress. To mitigate these issues, we developed OpenFactCheck, a unified framework, with three modules: (i) RESPONSEEVAL, which allows users to easily customize an automatic fact-checking system and to assess the factuality of all claims in an input document using that system, (ii) LLMEVAL, which assesses the overall factuality of an LLM, and (iii) CHECKEREVAL, a module to evaluate automatic fact-checking systems. OpenFactCheck is open-sourced (https://github.com/mbzuai-nlp/openfactcheck) and publicly released as a Python library (https://pypi.org/project/openfactcheck/) and also as a web service (http://app.openfactcheck.com). A video describing the system is available at https://youtu.be/-i9VKL0HleI.</abstract>
<identifier type="citekey">iqbal-etal-2024-openfactcheck</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-demo.23</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>219</start>
<end>229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs
%A Iqbal, Hasan
%A Wang, Yuxia
%A Wang, Minghan
%A Georgiev, Georgi Nenkov
%A Geng, Jiahui
%A Gurevych, Iryna
%A Nakov, Preslav
%Y Hernandez Farias, Delia Irazu
%Y Hope, Tom
%Y Li, Manling
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F iqbal-etal-2024-openfactcheck
%X The increased use of large language models (LLMs) across a variety of real-world applications calls for automatic tools to check the factual accuracy of their outputs, as LLMs often hallucinate. This is difficult as it requires assessing the factuality of free-form open-domain responses. While there has been a lot of research on this topic, different papers use different evaluation benchmarks and measures,which makes them hard to compare and hampers future progress. To mitigate these issues, we developed OpenFactCheck, a unified framework, with three modules: (i) RESPONSEEVAL, which allows users to easily customize an automatic fact-checking system and to assess the factuality of all claims in an input document using that system, (ii) LLMEVAL, which assesses the overall factuality of an LLM, and (iii) CHECKEREVAL, a module to evaluate automatic fact-checking systems. OpenFactCheck is open-sourced (https://github.com/mbzuai-nlp/openfactcheck) and publicly released as a Python library (https://pypi.org/project/openfactcheck/) and also as a web service (http://app.openfactcheck.com). A video describing the system is available at https://youtu.be/-i9VKL0HleI.
%U https://aclanthology.org/2024.emnlp-demo.23
%P 219-229
Markdown (Informal)
[OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs](https://aclanthology.org/2024.emnlp-demo.23) (Iqbal et al., EMNLP 2024)
ACL
- Hasan Iqbal, Yuxia Wang, Minghan Wang, Georgi Nenkov Georgiev, Jiahui Geng, Iryna Gurevych, and Preslav Nakov. 2024. OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 219–229, Miami, Florida, USA. Association for Computational Linguistics.