@inproceedings{herrlein-etal-2024-anhalten,
title = "{ANHALTEN}: Cross-Lingual Transfer for {G}erman Token-Level Reference-Free Hallucination Detection",
author = "Herrlein, Janek and
Hung, Chia-Chien and
Glava�, Goran",
editor = "Fu, Xiyan and
Fleisig, Eve",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-srw.18/",
doi = "10.18653/v1/2024.acl-srw.18",
pages = "92--100",
abstract = "Research on token-level reference-free hallucination detection has predominantly focused on English, primarily due to the scarcity of robust datasets in other languages. This has hindered systematic investigations into the effectiveness of cross-lingual transfer for this important NLP application. To address this gap, we introduce ANHALTEN, a new evaluation dataset that extends the English hallucination detection dataset to German. To the best of our knowledge, this is the first work that explores cross-lingual transfer for token-level reference-free hallucination detection. ANHALTEN contains gold annotations in German that are parallel (i.e., directly comparable to the original English instances). We benchmark several prominent cross-lingual transfer approaches, demonstrating that larger context length leads to better hallucination detection in German, even without succeeding context. Importantly, we show that the sample-efficient few-shot transfer is the most effective approach in most setups. This highlights the practical benefits of minimal annotation effort in the target language for reference-free hallucination detection. Aiming to catalyze future research on cross-lingual token-level reference-free hallucination detection, we make ANHALTEN publicly available: https://github.com/janekh24/anhalten"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herrlein-etal-2024-anhalten">
<titleInfo>
<title>ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janek</namePart>
<namePart type="family">Herrlein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Chien</namePart>
<namePart type="family">Hung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glava�</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research on token-level reference-free hallucination detection has predominantly focused on English, primarily due to the scarcity of robust datasets in other languages. This has hindered systematic investigations into the effectiveness of cross-lingual transfer for this important NLP application. To address this gap, we introduce ANHALTEN, a new evaluation dataset that extends the English hallucination detection dataset to German. To the best of our knowledge, this is the first work that explores cross-lingual transfer for token-level reference-free hallucination detection. ANHALTEN contains gold annotations in German that are parallel (i.e., directly comparable to the original English instances). We benchmark several prominent cross-lingual transfer approaches, demonstrating that larger context length leads to better hallucination detection in German, even without succeeding context. Importantly, we show that the sample-efficient few-shot transfer is the most effective approach in most setups. This highlights the practical benefits of minimal annotation effort in the target language for reference-free hallucination detection. Aiming to catalyze future research on cross-lingual token-level reference-free hallucination detection, we make ANHALTEN publicly available: https://github.com/janekh24/anhalten</abstract>
<identifier type="citekey">herrlein-etal-2024-anhalten</identifier>
<identifier type="doi">10.18653/v1/2024.acl-srw.18</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-srw.18/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>92</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination Detection
%A Herrlein, Janek
%A Hung, Chia-Chien
%A Glava�, Goran
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F herrlein-etal-2024-anhalten
%X Research on token-level reference-free hallucination detection has predominantly focused on English, primarily due to the scarcity of robust datasets in other languages. This has hindered systematic investigations into the effectiveness of cross-lingual transfer for this important NLP application. To address this gap, we introduce ANHALTEN, a new evaluation dataset that extends the English hallucination detection dataset to German. To the best of our knowledge, this is the first work that explores cross-lingual transfer for token-level reference-free hallucination detection. ANHALTEN contains gold annotations in German that are parallel (i.e., directly comparable to the original English instances). We benchmark several prominent cross-lingual transfer approaches, demonstrating that larger context length leads to better hallucination detection in German, even without succeeding context. Importantly, we show that the sample-efficient few-shot transfer is the most effective approach in most setups. This highlights the practical benefits of minimal annotation effort in the target language for reference-free hallucination detection. Aiming to catalyze future research on cross-lingual token-level reference-free hallucination detection, we make ANHALTEN publicly available: https://github.com/janekh24/anhalten
%R 10.18653/v1/2024.acl-srw.18
%U https://aclanthology.org/2024.luhme-srw.18/
%U https://doi.org/10.18653/v1/2024.acl-srw.18
%P 92-100
Markdown (Informal)
[ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination Detection](https://aclanthology.org/2024.luhme-srw.18/) (Herrlein et al., ACL 2024)
ACL