@inproceedings{liu-etal-2025-long,
title = "Long-form Hallucination Detection with Self-elicitation",
author = "Liu, Zihang and
Guo, Jiawei and
Zhang, Hao and
Chen, Hongyang and
Bu, Jiajun and
Wang, Haishuai",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.211/",
doi = "10.18653/v1/2025.findings-acl.211",
pages = "4082--4100",
ISBN = "979-8-89176-256-5",
abstract = "While Large Language Models (LLMs) have exhibited impressive performance in generating long-form content, they frequently present a hazard of producing factual inaccuracies or hallucinations. An effective strategy to mitigate this hazard is to leverage off-the-shelf LLMs to detect hallucinations after the generation. The primary challenge resides in the comprehensive elicitation of the intrinsic knowledge acquired during their pre-training phase. However, existing methods that employ multi-step reasoning chains predominantly fall short of addressing this issue. Moreover, since existing methods for hallucination detection tend to decompose text into isolated statements, they are unable to understand the contextual semantic relations in long-form content. In this paper, we study a novel concept, self-elicitation, to leverage self-generated thoughts derived from prior statements as catalysts to elicit the expression of intrinsic knowledge and understand contextual semantics. We present a framework, SelfElicit, to integrate self-elicitation with graph structures to effectively organize the elicited knowledge and facilitate factual evaluations. Extensive experiments on five datasets in various domains demonstrate the effectiveness of self-elicitation and the superiority of our proposed method."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-long">
<titleInfo>
<title>Long-form Hallucination Detection with Self-elicitation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Bu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haishuai</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>While Large Language Models (LLMs) have exhibited impressive performance in generating long-form content, they frequently present a hazard of producing factual inaccuracies or hallucinations. An effective strategy to mitigate this hazard is to leverage off-the-shelf LLMs to detect hallucinations after the generation. The primary challenge resides in the comprehensive elicitation of the intrinsic knowledge acquired during their pre-training phase. However, existing methods that employ multi-step reasoning chains predominantly fall short of addressing this issue. Moreover, since existing methods for hallucination detection tend to decompose text into isolated statements, they are unable to understand the contextual semantic relations in long-form content. In this paper, we study a novel concept, self-elicitation, to leverage self-generated thoughts derived from prior statements as catalysts to elicit the expression of intrinsic knowledge and understand contextual semantics. We present a framework, SelfElicit, to integrate self-elicitation with graph structures to effectively organize the elicited knowledge and facilitate factual evaluations. Extensive experiments on five datasets in various domains demonstrate the effectiveness of self-elicitation and the superiority of our proposed method.</abstract>
<identifier type="citekey">liu-etal-2025-long</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.211</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.211/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>4082</start>
<end>4100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Long-form Hallucination Detection with Self-elicitation
%A Liu, Zihang
%A Guo, Jiawei
%A Zhang, Hao
%A Chen, Hongyang
%A Bu, Jiajun
%A Wang, Haishuai
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F liu-etal-2025-long
%X While Large Language Models (LLMs) have exhibited impressive performance in generating long-form content, they frequently present a hazard of producing factual inaccuracies or hallucinations. An effective strategy to mitigate this hazard is to leverage off-the-shelf LLMs to detect hallucinations after the generation. The primary challenge resides in the comprehensive elicitation of the intrinsic knowledge acquired during their pre-training phase. However, existing methods that employ multi-step reasoning chains predominantly fall short of addressing this issue. Moreover, since existing methods for hallucination detection tend to decompose text into isolated statements, they are unable to understand the contextual semantic relations in long-form content. In this paper, we study a novel concept, self-elicitation, to leverage self-generated thoughts derived from prior statements as catalysts to elicit the expression of intrinsic knowledge and understand contextual semantics. We present a framework, SelfElicit, to integrate self-elicitation with graph structures to effectively organize the elicited knowledge and facilitate factual evaluations. Extensive experiments on five datasets in various domains demonstrate the effectiveness of self-elicitation and the superiority of our proposed method.
%R 10.18653/v1/2025.findings-acl.211
%U https://aclanthology.org/2025.findings-acl.211/
%U https://doi.org/10.18653/v1/2025.findings-acl.211
%P 4082-4100
Markdown (Informal)
[Long-form Hallucination Detection with Self-elicitation](https://aclanthology.org/2025.findings-acl.211/) (Liu et al., Findings 2025)
ACL
- Zihang Liu, Jiawei Guo, Hao Zhang, Hongyang Chen, Jiajun Bu, and Haishuai Wang. 2025. Long-form Hallucination Detection with Self-elicitation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4082–4100, Vienna, Austria. Association for Computational Linguistics.