@inproceedings{panda-etal-2025-accesseval,
title = "{A}ccess{E}val: Benchmarking Disability Bias in Large Language Models",
author = "Panda, Srikant and
Agarwal, Amit and
Patel, Hitesh Laxmichand",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1653/",
pages = "32492--32518",
ISBN = "979-8-89176-332-6",
abstract = "Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real life queries. To systematically investigate these effects with various disability context, we introduce AccessEval, a large-scale benchmark evaluating total 21 close {\&} open source LLMs across six real-world domains and nine disability types using paired Neutral and Disability-Aware Queries. We evaluated model outputs with metrics for factual accuracy, sentiment, and social perception.Our analysis reveals that responses to disability-aware queries tend to have higher factual error, more negative tone, and increased stereotyping with social perception compared to neutral queries. These effects show notable variation by domain and disability type. Disabilities affecting hearing, speech and mobility are disproportionately impacted. These disparities reveal persistent forms of ableism, highlighting the need for more comprehensive and nuanced assessment.We further argue that framing bias in terms of model performance within real-world decision making helps to better link model behaviors to the potential harms users may face. This approach guides the development of more effective and tailored fairness interventions. AccessEval, therefore, serves as a crucial tool for advancing equitable and inclusive language technologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="panda-etal-2025-accesseval">
<titleInfo>
<title>AccessEval: Benchmarking Disability Bias in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srikant</namePart>
<namePart type="family">Panda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitesh</namePart>
<namePart type="given">Laxmichand</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real life queries. To systematically investigate these effects with various disability context, we introduce AccessEval, a large-scale benchmark evaluating total 21 close & open source LLMs across six real-world domains and nine disability types using paired Neutral and Disability-Aware Queries. We evaluated model outputs with metrics for factual accuracy, sentiment, and social perception.Our analysis reveals that responses to disability-aware queries tend to have higher factual error, more negative tone, and increased stereotyping with social perception compared to neutral queries. These effects show notable variation by domain and disability type. Disabilities affecting hearing, speech and mobility are disproportionately impacted. These disparities reveal persistent forms of ableism, highlighting the need for more comprehensive and nuanced assessment.We further argue that framing bias in terms of model performance within real-world decision making helps to better link model behaviors to the potential harms users may face. This approach guides the development of more effective and tailored fairness interventions. AccessEval, therefore, serves as a crucial tool for advancing equitable and inclusive language technologies.</abstract>
<identifier type="citekey">panda-etal-2025-accesseval</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1653/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>32492</start>
<end>32518</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AccessEval: Benchmarking Disability Bias in Large Language Models
%A Panda, Srikant
%A Agarwal, Amit
%A Patel, Hitesh Laxmichand
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F panda-etal-2025-accesseval
%X Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real life queries. To systematically investigate these effects with various disability context, we introduce AccessEval, a large-scale benchmark evaluating total 21 close & open source LLMs across six real-world domains and nine disability types using paired Neutral and Disability-Aware Queries. We evaluated model outputs with metrics for factual accuracy, sentiment, and social perception.Our analysis reveals that responses to disability-aware queries tend to have higher factual error, more negative tone, and increased stereotyping with social perception compared to neutral queries. These effects show notable variation by domain and disability type. Disabilities affecting hearing, speech and mobility are disproportionately impacted. These disparities reveal persistent forms of ableism, highlighting the need for more comprehensive and nuanced assessment.We further argue that framing bias in terms of model performance within real-world decision making helps to better link model behaviors to the potential harms users may face. This approach guides the development of more effective and tailored fairness interventions. AccessEval, therefore, serves as a crucial tool for advancing equitable and inclusive language technologies.
%U https://aclanthology.org/2025.emnlp-main.1653/
%P 32492-32518
Markdown (Informal)
[AccessEval: Benchmarking Disability Bias in Large Language Models](https://aclanthology.org/2025.emnlp-main.1653/) (Panda et al., EMNLP 2025)
ACL