mlsanityData to 7 Oct 2026

Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs

arXiv 2605.20191 ↗First posted 2 Apr 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern Large Language Models (LLMs) have recently attracted much attention for their ability to simulate human behavior and generate text that reflects personas and demographic groups. While these capabilities can open up a multitude of diverse applications across fields, it is crucial to examine how such models represent various target groups since LLMs can perpetuate and amplify biases or discrimination against historically marginalized communities or, alternatively, as a result of debiasing efforts, overcorrect by portraying overly positive stereotypes. This overcompensation can idealize these groups, erasing the complexities and challenges they face in favor of unrealistic depictions. In this paper, we investigate how LLMs represent disability by simulating the perspectives of individuals with disabilities in generating social media posts. These posts are then compared with those written by real people with disabilities, focusing on emotional tone, sentiment, and representative words and themes. Our analysis reveals two key findings: (1) LLMs often idealize the experiences of people with disabilities, producing overly positive stereotypes that, despite appearing uplifting, fail to authentically capture their lived realities; and (2) a comparative analysis of posts simulating individuals with and without disabilities highlights a negative bias, where certain topics, such as career and entertainment, are disproportionately associated with nondisabled individuals. This reinforces exclusionary narratives and over-idealized portrayals of disability, misrepresenting the actual challenges faced by this community. These findings align with broader concerns and ongoing research showing that LLMs struggle to reflect the diverse realities of society, particularly the nuanced experiences of marginalized groups, and underscore the need for critical scrutiny of their representations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 62 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

28 of 62 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  3. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  4. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  5. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  6. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  8. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  9. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
  10. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  11. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  12. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
16 more
  1. 2013Crowdsourcing a Word-Emotion Association Lexiconcited by 193
  2. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  3. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  4. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 160
  5. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 146
  6. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  7. 2023The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspectivecited by 57
  8. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  9. 2022Perturbation Augmentation for Fairer NLPcited by 51
  10. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  11. 2024BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Datacited by 49
  12. 2023The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendationscited by 41
  13. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  14. 2024Identifying and Improving Disability Bias in GPT-Based Resume Screeningcited by 27
  15. 2025Inclusive Education with AI: Supporting Special Needs and Tackling Language Barrierscited by 2
  16. 2025Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generationcited by 2

Built on by

Not cited yet.