<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2023-detecting">
    <titleInfo>
        <title>Detecting and Mitigating Hallucinations in Multilingual Summarisation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yifu</namePart>
        <namePart type="family">Qiu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yftah</namePart>
        <namePart type="family">Ziser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Korhonen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Edoardo</namePart>
        <namePart type="family">Ponti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shay</namePart>
        <namePart type="family">Cohen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lack faithfulness to the original document. This issue becomes even more pronounced in low-resource languages, where summarisation requires cross-lingual transfer. With the existing faithful metrics focusing on English, even measuring the extent of this phenomenon in cross-lingual settings is hard. To address this, we first develop a novel metric, mFACT, evaluating the faithfulness of non-English summaries, leveraging translation-based transfer from multiple English faithfulness metrics. Through extensive experiments in multiple languages, we demonstrate that mFACT is best suited to detect hallucinations compared to alternative metrics. With mFACT, we assess a broad range of multilingual large language models, and find that they all tend to hallucinate often in languages different from English. We then propose a simple but effective method to reduce hallucinations in cross-lingual transfer, which weighs the loss of each training example by its faithfulness score. This method drastically increases both performance and faithfulness according to both automatic and human evaluation when compared to strong baselines for cross-lingual transfer such as MAD-X. Our code and dataset are available at https://github.com/yfqiu-nlp/mfact-summ.</abstract>
    <identifier type="citekey">qiu-etal-2023-detecting</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.551</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.551</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>8914</start>
            <end>8932</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Detecting and Mitigating Hallucinations in Multilingual Summarisation
%A Qiu, Yifu
%A Ziser, Yftah
%A Korhonen, Anna
%A Ponti, Edoardo
%A Cohen, Shay
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F qiu-etal-2023-detecting
%X Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lack faithfulness to the original document. This issue becomes even more pronounced in low-resource languages, where summarisation requires cross-lingual transfer. With the existing faithful metrics focusing on English, even measuring the extent of this phenomenon in cross-lingual settings is hard. To address this, we first develop a novel metric, mFACT, evaluating the faithfulness of non-English summaries, leveraging translation-based transfer from multiple English faithfulness metrics. Through extensive experiments in multiple languages, we demonstrate that mFACT is best suited to detect hallucinations compared to alternative metrics. With mFACT, we assess a broad range of multilingual large language models, and find that they all tend to hallucinate often in languages different from English. We then propose a simple but effective method to reduce hallucinations in cross-lingual transfer, which weighs the loss of each training example by its faithfulness score. This method drastically increases both performance and faithfulness according to both automatic and human evaluation when compared to strong baselines for cross-lingual transfer such as MAD-X. Our code and dataset are available at https://github.com/yfqiu-nlp/mfact-summ.
%R 10.18653/v1/2023.emnlp-main.551
%U https://aclanthology.org/2023.emnlp-main.551
%U https://doi.org/10.18653/v1/2023.emnlp-main.551
%P 8914-8932

Markdown (Informal)

[Detecting and Mitigating Hallucinations in Multilingual Summarisation](https://aclanthology.org/2023.emnlp-main.551) (Qiu et al., EMNLP 2023)

• Detecting and Mitigating Hallucinations in Multilingual Summarisation (Qiu et al., EMNLP 2023)

ACL

• Yifu Qiu, Yftah Ziser, Anna Korhonen, Edoardo Ponti, and Shay Cohen. 2023. Detecting and Mitigating Hallucinations in Multilingual Summarisation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8914–8932, Singapore. Association for Computational Linguistics.