@inproceedings{bang-etal-2025-hallulens,
title = "{H}allu{L}ens: {LLM} Hallucination Benchmark",
author = "Bang, Yejin and
Ji, Ziwei and
Schelten, Alan and
Hartshorn, Anthony and
Fowler, Tara and
Zhang, Cheng and
Cancedda, Nicola and
Fung, Pascale",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1176/",
doi = "10.18653/v1/2025.acl-long.1176",
pages = "24128--24156",
ISBN = "979-8-89176-251-0",
abstract = "Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as ``hallucination.'' These hallucinations undermine user trust and hinder the adoption of generative AI systems. Addressing hallucinations is important for the advancement of LLMs. This paper introduces a comprehensive hallucination benchmark HalluLens, incorporating both extrinsic and intrinsic evaluation tasks, built upon a clear taxonomy of hallucination. A major challenge in benchmarking hallucinations is the lack of a unified framework due to inconsistent definitions and categorizations. We disentangle LLM hallucination from ``factuality'' and propose a taxonomy distinguishing extrinsic and intrinsic hallucinations to promote consistency and facilitate research. We emphasize extrinsic hallucinations {--} where generated content deviates from training data {--} as they become increasingly relevant with LLM advancements. However, no benchmark is solely dedicated to extrinsic hallucinations. To address this gap, HalluLens introduces three new extrinsic tasks with dynamic test set generation to mitigate data leakage and ensure robustness. We release codebase for extrinsic hallucination benchmark."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bang-etal-2025-hallulens">
<titleInfo>
<title>HalluLens: LLM Hallucination Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Bang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Schelten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Hartshorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Fowler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Cancedda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as “hallucination.” These hallucinations undermine user trust and hinder the adoption of generative AI systems. Addressing hallucinations is important for the advancement of LLMs. This paper introduces a comprehensive hallucination benchmark HalluLens, incorporating both extrinsic and intrinsic evaluation tasks, built upon a clear taxonomy of hallucination. A major challenge in benchmarking hallucinations is the lack of a unified framework due to inconsistent definitions and categorizations. We disentangle LLM hallucination from “factuality” and propose a taxonomy distinguishing extrinsic and intrinsic hallucinations to promote consistency and facilitate research. We emphasize extrinsic hallucinations – where generated content deviates from training data – as they become increasingly relevant with LLM advancements. However, no benchmark is solely dedicated to extrinsic hallucinations. To address this gap, HalluLens introduces three new extrinsic tasks with dynamic test set generation to mitigate data leakage and ensure robustness. We release codebase for extrinsic hallucination benchmark.</abstract>
<identifier type="citekey">bang-etal-2025-hallulens</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1176</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1176/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>24128</start>
<end>24156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HalluLens: LLM Hallucination Benchmark
%A Bang, Yejin
%A Ji, Ziwei
%A Schelten, Alan
%A Hartshorn, Anthony
%A Fowler, Tara
%A Zhang, Cheng
%A Cancedda, Nicola
%A Fung, Pascale
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F bang-etal-2025-hallulens
%X Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as “hallucination.” These hallucinations undermine user trust and hinder the adoption of generative AI systems. Addressing hallucinations is important for the advancement of LLMs. This paper introduces a comprehensive hallucination benchmark HalluLens, incorporating both extrinsic and intrinsic evaluation tasks, built upon a clear taxonomy of hallucination. A major challenge in benchmarking hallucinations is the lack of a unified framework due to inconsistent definitions and categorizations. We disentangle LLM hallucination from “factuality” and propose a taxonomy distinguishing extrinsic and intrinsic hallucinations to promote consistency and facilitate research. We emphasize extrinsic hallucinations – where generated content deviates from training data – as they become increasingly relevant with LLM advancements. However, no benchmark is solely dedicated to extrinsic hallucinations. To address this gap, HalluLens introduces three new extrinsic tasks with dynamic test set generation to mitigate data leakage and ensure robustness. We release codebase for extrinsic hallucination benchmark.
%R 10.18653/v1/2025.acl-long.1176
%U https://aclanthology.org/2025.acl-long.1176/
%U https://doi.org/10.18653/v1/2025.acl-long.1176
%P 24128-24156
Markdown (Informal)
[HalluLens: LLM Hallucination Benchmark](https://aclanthology.org/2025.acl-long.1176/) (Bang et al., ACL 2025)
ACL
- Yejin Bang, Ziwei Ji, Alan Schelten, Anthony Hartshorn, Tara Fowler, Cheng Zhang, Nicola Cancedda, and Pascale Fung. 2025. HalluLens: LLM Hallucination Benchmark. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 24128–24156, Vienna, Austria. Association for Computational Linguistics.