@inproceedings{rashad-etal-2024-factalign,
title = "{F}act{A}lign: Fact-Level Hallucination Detection and Classification Through Knowledge Graph Alignment",
author = "Rashad, Mohamed and
Zahran, Ahmed and
Amin, Abanoub and
Abdelaal, Amr and
Altantawy, Mohamed",
editor = "Ovalle, Anaelia and
Chang, Kai-Wei and
Cao, Yang Trista and
Mehrabi, Ninareh and
Zhao, Jieyu and
Galstyan, Aram and
Dhamala, Jwala and
Kumar, Anoop and
Gupta, Rahul",
booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.trustnlp-1.8",
doi = "10.18653/v1/2024.trustnlp-1.8",
pages = "79--84",
abstract = "This paper proposes a novel black-box approach for fact-level hallucination detection and classification by transforming the problem into a knowledge graph alignment task. This approach allows us to classify detected hallucinations as either intrinsic or extrinsic. The paper starts by discussing the field of hallucination detection and introducing several approaches to related work. Then, we introduce the proposed FactAlign approach for hallucination detection and discuss how we can use it to classify hallucinations as either intrinsic or extrinsic. Experiments are carried out to evaluate the proposed method against state-of-the-art methods on the hallucination detection task using the WikiBio GPT-3 hallucination dataset, and on the hallucination type classification task using the XSum hallucination annotations dataset. The experimental results show that our method achieves a 0.889 F1 score for the hallucination detection and 0.825 F1 for the hallucination type classification, without any further training, fine-tuning, or producing multiple samples of the LLM response.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rashad-etal-2024-factalign">
<titleInfo>
<title>FactAlign: Fact-Level Hallucination Detection and Classification Through Knowledge Graph Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Rashad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Zahran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abanoub</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Abdelaal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Altantawy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Trista</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galstyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes a novel black-box approach for fact-level hallucination detection and classification by transforming the problem into a knowledge graph alignment task. This approach allows us to classify detected hallucinations as either intrinsic or extrinsic. The paper starts by discussing the field of hallucination detection and introducing several approaches to related work. Then, we introduce the proposed FactAlign approach for hallucination detection and discuss how we can use it to classify hallucinations as either intrinsic or extrinsic. Experiments are carried out to evaluate the proposed method against state-of-the-art methods on the hallucination detection task using the WikiBio GPT-3 hallucination dataset, and on the hallucination type classification task using the XSum hallucination annotations dataset. The experimental results show that our method achieves a 0.889 F1 score for the hallucination detection and 0.825 F1 for the hallucination type classification, without any further training, fine-tuning, or producing multiple samples of the LLM response.</abstract>
<identifier type="citekey">rashad-etal-2024-factalign</identifier>
<identifier type="doi">10.18653/v1/2024.trustnlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2024.trustnlp-1.8</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>79</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FactAlign: Fact-Level Hallucination Detection and Classification Through Knowledge Graph Alignment
%A Rashad, Mohamed
%A Zahran, Ahmed
%A Amin, Abanoub
%A Abdelaal, Amr
%A Altantawy, Mohamed
%Y Ovalle, Anaelia
%Y Chang, Kai-Wei
%Y Cao, Yang Trista
%Y Mehrabi, Ninareh
%Y Zhao, Jieyu
%Y Galstyan, Aram
%Y Dhamala, Jwala
%Y Kumar, Anoop
%Y Gupta, Rahul
%S Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F rashad-etal-2024-factalign
%X This paper proposes a novel black-box approach for fact-level hallucination detection and classification by transforming the problem into a knowledge graph alignment task. This approach allows us to classify detected hallucinations as either intrinsic or extrinsic. The paper starts by discussing the field of hallucination detection and introducing several approaches to related work. Then, we introduce the proposed FactAlign approach for hallucination detection and discuss how we can use it to classify hallucinations as either intrinsic or extrinsic. Experiments are carried out to evaluate the proposed method against state-of-the-art methods on the hallucination detection task using the WikiBio GPT-3 hallucination dataset, and on the hallucination type classification task using the XSum hallucination annotations dataset. The experimental results show that our method achieves a 0.889 F1 score for the hallucination detection and 0.825 F1 for the hallucination type classification, without any further training, fine-tuning, or producing multiple samples of the LLM response.
%R 10.18653/v1/2024.trustnlp-1.8
%U https://aclanthology.org/2024.trustnlp-1.8
%U https://doi.org/10.18653/v1/2024.trustnlp-1.8
%P 79-84
Markdown (Informal)
[FactAlign: Fact-Level Hallucination Detection and Classification Through Knowledge Graph Alignment](https://aclanthology.org/2024.trustnlp-1.8) (Rashad et al., TrustNLP-WS 2024)
ACL