@inproceedings{zhang-etal-2026-poly,
title = "Poly-{FEVER}: A Multilingual Hallucination Detection Benchmark",
author = "Zhang, Hanzhi and
Anjum, Sumera and
Fan, Heng and
Zheng, Weijian and
Huang, Yan and
Feng, Yunhe",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.540/",
pages = "11353--11369",
ISBN = "979-8-89176-462-0",
abstract = "We present Poly-FEVER, an open-source large-scale multilingual benchmark for hallucination detection through controlled factuality judgment in large language models. Poly-FEVER extends FEVER, Climate-FEVER, and SciFact to 77,973 Supported/Refuted claims aligned across 11 languages. We augment each claim with topic metadata from a 22-topic LDA model, enabling topic-aware analysis of multilingual factuality behavior. Translations are produced with Google Cloud Translation and validated by a targeted human audit, GEMBA, and COMETKiwi. We benchmark ChatGPT-3.5, LLaMA-2/3, Phi-3.5, and Mistral across three prompt families and evaluate robustness to model-generated rephrasing. We further analyze resource imbalance using web presence as a proxy for online claim availability, and evaluate retrieval-augmented factuality judgment with DPR over Wikipedia. Results show pronounced cross-lingual disparities under aligned claims, with stronger accuracy in high-resource languages such as English and Chinese and weaker accuracy in lower-resource languages such as Amharic and Tamil. Topic-aware prompting and retrieval provide selective gains, especially in Arabic and Amharic, while their effects vary across languages and can conflict with model priors. Poly-FEVER establishes a rigorous resource for responsible, language-adaptive hallucination detection and language-sensitive factuality evaluation. The proposed Poly-FEVER is available at: https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-poly">
<titleInfo>
<title>Poly-FEVER: A Multilingual Hallucination Detection Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanzhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumera</namePart>
<namePart type="family">Anjum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijian</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunhe</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>We present Poly-FEVER, an open-source large-scale multilingual benchmark for hallucination detection through controlled factuality judgment in large language models. Poly-FEVER extends FEVER, Climate-FEVER, and SciFact to 77,973 Supported/Refuted claims aligned across 11 languages. We augment each claim with topic metadata from a 22-topic LDA model, enabling topic-aware analysis of multilingual factuality behavior. Translations are produced with Google Cloud Translation and validated by a targeted human audit, GEMBA, and COMETKiwi. We benchmark ChatGPT-3.5, LLaMA-2/3, Phi-3.5, and Mistral across three prompt families and evaluate robustness to model-generated rephrasing. We further analyze resource imbalance using web presence as a proxy for online claim availability, and evaluate retrieval-augmented factuality judgment with DPR over Wikipedia. Results show pronounced cross-lingual disparities under aligned claims, with stronger accuracy in high-resource languages such as English and Chinese and weaker accuracy in lower-resource languages such as Amharic and Tamil. Topic-aware prompting and retrieval provide selective gains, especially in Arabic and Amharic, while their effects vary across languages and can conflict with model priors. Poly-FEVER establishes a rigorous resource for responsible, language-adaptive hallucination detection and language-sensitive factuality evaluation. The proposed Poly-FEVER is available at: https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER.</abstract>
<identifier type="citekey">zhang-etal-2026-poly</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.540/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>11353</start>
<end>11369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Poly-FEVER: A Multilingual Hallucination Detection Benchmark
%A Zhang, Hanzhi
%A Anjum, Sumera
%A Fan, Heng
%A Zheng, Weijian
%A Huang, Yan
%A Feng, Yunhe
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhang-etal-2026-poly
%X We present Poly-FEVER, an open-source large-scale multilingual benchmark for hallucination detection through controlled factuality judgment in large language models. Poly-FEVER extends FEVER, Climate-FEVER, and SciFact to 77,973 Supported/Refuted claims aligned across 11 languages. We augment each claim with topic metadata from a 22-topic LDA model, enabling topic-aware analysis of multilingual factuality behavior. Translations are produced with Google Cloud Translation and validated by a targeted human audit, GEMBA, and COMETKiwi. We benchmark ChatGPT-3.5, LLaMA-2/3, Phi-3.5, and Mistral across three prompt families and evaluate robustness to model-generated rephrasing. We further analyze resource imbalance using web presence as a proxy for online claim availability, and evaluate retrieval-augmented factuality judgment with DPR over Wikipedia. Results show pronounced cross-lingual disparities under aligned claims, with stronger accuracy in high-resource languages such as English and Chinese and weaker accuracy in lower-resource languages such as Amharic and Tamil. Topic-aware prompting and retrieval provide selective gains, especially in Arabic and Amharic, while their effects vary across languages and can conflict with model priors. Poly-FEVER establishes a rigorous resource for responsible, language-adaptive hallucination detection and language-sensitive factuality evaluation. The proposed Poly-FEVER is available at: https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER.
%U https://aclanthology.org/2026.findings-emnlp.540/
%P 11353-11369
Markdown (Informal)
[Poly-FEVER: A Multilingual Hallucination Detection Benchmark](https://aclanthology.org/2026.findings-emnlp.540/) (Zhang et al., Findings 2026)
ACL
- Hanzhi Zhang, Sumera Anjum, Heng Fan, Weijian Zheng, Yan Huang, and Yunhe Feng. 2026. Poly-FEVER: A Multilingual Hallucination Detection Benchmark. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 11353–11369, Budapest, Hungary. Association for Computational Linguistics.