@inproceedings{li-etal-2026-hallucination,
title = "Hallucination Detection in Long-Form Text Generated by {LLM}s: A Benchmark and a Hyper-Relational Knowledge Graph Approach",
author = "Li, Zituo and
Chen, Guangzhou and
Sun, Jianbin and
Song, Qi and
Kewei, Yang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1673/",
pages = "33477--33494",
ISBN = "979-8-89176-395-1",
abstract = "Hallucination detection has attracted increasing attention, particularly in long-form text generation, where language models are more prone to producing factually inaccurate content. Prior studies reveal two limitations: (1) current benchmarks focus on short-form content, lacking the structural complexity required in long-form scenarios; (2) existing methods are constrained by coarse-grained consistency checks and fail to capture long-range and hyper-relational dependencies. To address these challenges, we provide LHD, a benchmark for long-form hallucination detection that contains diverse entity types and intricate factual dependencies spanning extended contexts. We further propose HRKG-HD, a zero-resource, black-box framework that models responses as fact-centric hyper-relational knowledge graphs and detects hallucinations through relation-aware multi-hop reasoning over these graphs. By linking distant facts through shared entities and qualifiers, this design enables a global and dependency-aware verification of factual consistency. Extensive experiments demonstrate that HRKG-HD not only outperforms existing baselines but also exhibits robust and consistent performance across various LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-hallucination">
<titleInfo>
<title>Hallucination Detection in Long-Form Text Generated by LLMs: A Benchmark and a Hyper-Relational Knowledge Graph Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zituo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangzhou</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianbin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Kewei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Hallucination detection has attracted increasing attention, particularly in long-form text generation, where language models are more prone to producing factually inaccurate content. Prior studies reveal two limitations: (1) current benchmarks focus on short-form content, lacking the structural complexity required in long-form scenarios; (2) existing methods are constrained by coarse-grained consistency checks and fail to capture long-range and hyper-relational dependencies. To address these challenges, we provide LHD, a benchmark for long-form hallucination detection that contains diverse entity types and intricate factual dependencies spanning extended contexts. We further propose HRKG-HD, a zero-resource, black-box framework that models responses as fact-centric hyper-relational knowledge graphs and detects hallucinations through relation-aware multi-hop reasoning over these graphs. By linking distant facts through shared entities and qualifiers, this design enables a global and dependency-aware verification of factual consistency. Extensive experiments demonstrate that HRKG-HD not only outperforms existing baselines but also exhibits robust and consistent performance across various LLMs.</abstract>
<identifier type="citekey">li-etal-2026-hallucination</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1673/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33477</start>
<end>33494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hallucination Detection in Long-Form Text Generated by LLMs: A Benchmark and a Hyper-Relational Knowledge Graph Approach
%A Li, Zituo
%A Chen, Guangzhou
%A Sun, Jianbin
%A Song, Qi
%A Kewei, Yang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F li-etal-2026-hallucination
%X Hallucination detection has attracted increasing attention, particularly in long-form text generation, where language models are more prone to producing factually inaccurate content. Prior studies reveal two limitations: (1) current benchmarks focus on short-form content, lacking the structural complexity required in long-form scenarios; (2) existing methods are constrained by coarse-grained consistency checks and fail to capture long-range and hyper-relational dependencies. To address these challenges, we provide LHD, a benchmark for long-form hallucination detection that contains diverse entity types and intricate factual dependencies spanning extended contexts. We further propose HRKG-HD, a zero-resource, black-box framework that models responses as fact-centric hyper-relational knowledge graphs and detects hallucinations through relation-aware multi-hop reasoning over these graphs. By linking distant facts through shared entities and qualifiers, this design enables a global and dependency-aware verification of factual consistency. Extensive experiments demonstrate that HRKG-HD not only outperforms existing baselines but also exhibits robust and consistent performance across various LLMs.
%U https://aclanthology.org/2026.findings-acl.1673/
%P 33477-33494
Markdown (Informal)
[Hallucination Detection in Long-Form Text Generated by LLMs: A Benchmark and a Hyper-Relational Knowledge Graph Approach](https://aclanthology.org/2026.findings-acl.1673/) (Li et al., Findings 2026)
ACL