<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="munis-etal-2026-fiber">
    <titleInfo>
        <title>FIBER: A Multilingual Evaluation Resource for Factual Inference Bias</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Evren</namePart>
        <namePart type="given">Ayberk</namePart>
        <namePart type="family">Munis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deniz</namePart>
        <namePart type="family">Yilmaz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arianna</namePart>
        <namePart type="family">Muti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cagri</namePart>
        <namePart type="family">Toraman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large language models are widely used across domains, yet there are concerns about their factual reliability and biases. Factual knowledge probing offers a systematic means to evaluate these aspects. Most existing benchmarks focus on single-entity facts and monolingual data. We therefore present FIBER, a multilingual benchmark for evaluating factual knowledge in single- and multi-entity settings. The dataset includes sentence completion, question-answering, and object-count prediction tasks in English, Italian, and Turkish. Using FIBER, we examine whether the prompt language induces inference bias in entity selection and how large language models perform on multi-entity versus single-entity questions. The results indicate that the language of the prompt can influence the model’s generated output, particularly for entities associated with the country corresponding to that language. However, this effect varies across different topics such that 31% of the topics exhibit factual inference bias score greater than 0.5. Moreover, the level of bias differs across languages such that Turkish prompts show higher bias compared to Italian in 83% of the topics, suggesting a language-dependent pattern. Our findings also show that models face greater difficulty when handling multi-entity questions than the single-entity questions. Model performance differs across both languages and model sizes. The highest mean average precision is achieved in English, while Turkish and Italian lead to noticeably lower scores. Larger models, including Llama-3.1-8B and Qwen-2.5-7B, show consistently better performance than smaller 3B-4B models.</abstract>
    <identifier type="citekey">munis-etal-2026-fiber</identifier>
    <identifier type="doi">10.63317/32j8kpkoevin</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.95/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>1205</start>
            <end>1215</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FIBER: A Multilingual Evaluation Resource for Factual Inference Bias
%A Munis, Evren Ayberk
%A Yilmaz, Deniz
%A Muti, Arianna
%A Toraman, Cagri
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F munis-etal-2026-fiber
%X Large language models are widely used across domains, yet there are concerns about their factual reliability and biases. Factual knowledge probing offers a systematic means to evaluate these aspects. Most existing benchmarks focus on single-entity facts and monolingual data. We therefore present FIBER, a multilingual benchmark for evaluating factual knowledge in single- and multi-entity settings. The dataset includes sentence completion, question-answering, and object-count prediction tasks in English, Italian, and Turkish. Using FIBER, we examine whether the prompt language induces inference bias in entity selection and how large language models perform on multi-entity versus single-entity questions. The results indicate that the language of the prompt can influence the model’s generated output, particularly for entities associated with the country corresponding to that language. However, this effect varies across different topics such that 31% of the topics exhibit factual inference bias score greater than 0.5. Moreover, the level of bias differs across languages such that Turkish prompts show higher bias compared to Italian in 83% of the topics, suggesting a language-dependent pattern. Our findings also show that models face greater difficulty when handling multi-entity questions than the single-entity questions. Model performance differs across both languages and model sizes. The highest mean average precision is achieved in English, while Turkish and Italian lead to noticeably lower scores. Larger models, including Llama-3.1-8B and Qwen-2.5-7B, show consistently better performance than smaller 3B-4B models.
%R 10.63317/32j8kpkoevin
%U https://aclanthology.org/2026.lrec-1.95/
%U https://doi.org/10.63317/32j8kpkoevin
%P 1205-1215

Markdown (Informal)

[FIBER: A Multilingual Evaluation Resource for Factual Inference Bias](https://aclanthology.org/2026.lrec-1.95/) (Munis et al., LREC 2026)

• FIBER: A Multilingual Evaluation Resource for Factual Inference Bias (Munis et al., LREC 2026)

ACL

• Evren Ayberk Munis, Deniz Yilmaz, Arianna Muti, and Cagri Toraman. 2026. FIBER: A Multilingual Evaluation Resource for Factual Inference Bias. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1205–1215, Palma de Mallorca, Spain. ELRA Language Resource Association.