@inproceedings{gupta-etal-2025-consistency,
title = "Consistency Is the Key: Detecting Hallucinations in {LLM} Generated Text By Checking Inconsistencies About Key Facts",
author = "Gupta, Raavi and
Panicker, Pranav Hari and
Bhatia, Sumit and
Ramakrishnan, Ganesh",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.129/",
pages = "2053--2068",
ISBN = "979-8-89176-303-6",
abstract = "Large language models (LLMs), despite their remarkable text generation capabilities, often hallucinate and generate text that is factually incorrect and not grounded in real-world knowledge. This poses serious risks in domains like healthcare, finance, and customer support. A typical way to use LLMs is via the APIs provided by LLM vendors where there is no access to model weights or options to fine-tune the model. Existing methods to detect hallucinations in such settings where the model access is restricted or constrained by resources typically require making multiple LLM API calls, increasing latency and API cost. We introduce CONFACTCHECK, an efficient hallucination detection approach that does not leverage any external knowledge base and works on the simple intuition that responses to factual probes within the generated text should be consistent within a single LLM and across different LLMs. Rigorous empirical evaluation on multiple datasets that cover both the generation of factual texts and the open generation shows that CONFACTCHECK can detect hallucinated facts efficiently using fewer resources and achieves higher accuracy scores compared to existing baselines that operate under similar conditions. Our code is available here."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2025-consistency">
<titleInfo>
<title>Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raavi</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="given">Hari</namePart>
<namePart type="family">Panicker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumit</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs), despite their remarkable text generation capabilities, often hallucinate and generate text that is factually incorrect and not grounded in real-world knowledge. This poses serious risks in domains like healthcare, finance, and customer support. A typical way to use LLMs is via the APIs provided by LLM vendors where there is no access to model weights or options to fine-tune the model. Existing methods to detect hallucinations in such settings where the model access is restricted or constrained by resources typically require making multiple LLM API calls, increasing latency and API cost. We introduce CONFACTCHECK, an efficient hallucination detection approach that does not leverage any external knowledge base and works on the simple intuition that responses to factual probes within the generated text should be consistent within a single LLM and across different LLMs. Rigorous empirical evaluation on multiple datasets that cover both the generation of factual texts and the open generation shows that CONFACTCHECK can detect hallucinated facts efficiently using fewer resources and achieves higher accuracy scores compared to existing baselines that operate under similar conditions. Our code is available here.</abstract>
<identifier type="citekey">gupta-etal-2025-consistency</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.129/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2053</start>
<end>2068</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts
%A Gupta, Raavi
%A Panicker, Pranav Hari
%A Bhatia, Sumit
%A Ramakrishnan, Ganesh
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F gupta-etal-2025-consistency
%X Large language models (LLMs), despite their remarkable text generation capabilities, often hallucinate and generate text that is factually incorrect and not grounded in real-world knowledge. This poses serious risks in domains like healthcare, finance, and customer support. A typical way to use LLMs is via the APIs provided by LLM vendors where there is no access to model weights or options to fine-tune the model. Existing methods to detect hallucinations in such settings where the model access is restricted or constrained by resources typically require making multiple LLM API calls, increasing latency and API cost. We introduce CONFACTCHECK, an efficient hallucination detection approach that does not leverage any external knowledge base and works on the simple intuition that responses to factual probes within the generated text should be consistent within a single LLM and across different LLMs. Rigorous empirical evaluation on multiple datasets that cover both the generation of factual texts and the open generation shows that CONFACTCHECK can detect hallucinated facts efficiently using fewer resources and achieves higher accuracy scores compared to existing baselines that operate under similar conditions. Our code is available here.
%U https://aclanthology.org/2025.findings-ijcnlp.129/
%P 2053-2068
Markdown (Informal)
[Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts](https://aclanthology.org/2025.findings-ijcnlp.129/) (Gupta et al., Findings 2025)
ACL