@inproceedings{kaneko-etal-2026-multilingual,
title = "A Multilingual Social Bias Benchmark Incorporating Thinking Processes",
author = "Kaneko, Masahiro and
Bollegala, Danushka and
Baldwin, Timothy",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2204/",
pages = "47726--47741",
ISBN = "979-8-89176-390-6",
abstract = "Large Language Models (LLMs) can learn both useful knowledge and harmful stereotypes, making bias evaluation essential.Existing frameworks fall into two types: those considering reasoning steps (Thinking Process-Aware Evaluation, TPAE) and those focusing only on final outputs (Straight-to-the-Answer Evaluation, SAE).Prior TPAE studies showed effectiveness in assessing gender bias but relied on template-based, word-counting prompts, limiting generalization to other bias types, languages, and reasoning-based methods.In this study, we introduce MBTP, a multilingual social bias benchmark that incorporates human-generated pro- and anti-stereotype reasoning as part of the thinking process, and propose a few-shot meta-evaluation method that enables scalable bias assessment without model fine-tuning.From experiments evaluating 13 social bias categories across 8 languages, we find that human-generated thinking consistently yields higher-quality evaluations than LLM-generated or template-based approaches.Furthermore, TPAE demonstrates superior performance over SAE, highlighting the importance of considering reasoning processes in bias evaluation.We will release the MBTP dataset upon paper acceptance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaneko-etal-2026-multilingual">
<titleInfo>
<title>A Multilingual Social Bias Benchmark Incorporating Thinking Processes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masahiro</namePart>
<namePart type="family">Kaneko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) can learn both useful knowledge and harmful stereotypes, making bias evaluation essential.Existing frameworks fall into two types: those considering reasoning steps (Thinking Process-Aware Evaluation, TPAE) and those focusing only on final outputs (Straight-to-the-Answer Evaluation, SAE).Prior TPAE studies showed effectiveness in assessing gender bias but relied on template-based, word-counting prompts, limiting generalization to other bias types, languages, and reasoning-based methods.In this study, we introduce MBTP, a multilingual social bias benchmark that incorporates human-generated pro- and anti-stereotype reasoning as part of the thinking process, and propose a few-shot meta-evaluation method that enables scalable bias assessment without model fine-tuning.From experiments evaluating 13 social bias categories across 8 languages, we find that human-generated thinking consistently yields higher-quality evaluations than LLM-generated or template-based approaches.Furthermore, TPAE demonstrates superior performance over SAE, highlighting the importance of considering reasoning processes in bias evaluation.We will release the MBTP dataset upon paper acceptance.</abstract>
<identifier type="citekey">kaneko-etal-2026-multilingual</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2204/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>47726</start>
<end>47741</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multilingual Social Bias Benchmark Incorporating Thinking Processes
%A Kaneko, Masahiro
%A Bollegala, Danushka
%A Baldwin, Timothy
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F kaneko-etal-2026-multilingual
%X Large Language Models (LLMs) can learn both useful knowledge and harmful stereotypes, making bias evaluation essential.Existing frameworks fall into two types: those considering reasoning steps (Thinking Process-Aware Evaluation, TPAE) and those focusing only on final outputs (Straight-to-the-Answer Evaluation, SAE).Prior TPAE studies showed effectiveness in assessing gender bias but relied on template-based, word-counting prompts, limiting generalization to other bias types, languages, and reasoning-based methods.In this study, we introduce MBTP, a multilingual social bias benchmark that incorporates human-generated pro- and anti-stereotype reasoning as part of the thinking process, and propose a few-shot meta-evaluation method that enables scalable bias assessment without model fine-tuning.From experiments evaluating 13 social bias categories across 8 languages, we find that human-generated thinking consistently yields higher-quality evaluations than LLM-generated or template-based approaches.Furthermore, TPAE demonstrates superior performance over SAE, highlighting the importance of considering reasoning processes in bias evaluation.We will release the MBTP dataset upon paper acceptance.
%U https://aclanthology.org/2026.acl-long.2204/
%P 47726-47741
Markdown (Informal)
[A Multilingual Social Bias Benchmark Incorporating Thinking Processes](https://aclanthology.org/2026.acl-long.2204/) (Kaneko et al., ACL 2026)
ACL
- Masahiro Kaneko, Danushka Bollegala, and Timothy Baldwin. 2026. A Multilingual Social Bias Benchmark Incorporating Thinking Processes. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 47726–47741, San Diego, California, United States. Association for Computational Linguistics.