mlsanityData to 14 Oct 2026

Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities

arXiv 2607.26062 ↗First posted 16 Jun 2026cs.CY cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Background: This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intellectual disabilities (ID). Objective: The study aims to identify and measure representational differences related to people with ID and examine them to identify implicit biases inherent in AI chat generation technologies. Methods: Utilizing the GPT-4-Turbo model, we requested story-generation based on 10 prompt stems with and without descriptors for ID. This process was repeated using four other LLMs (OpenAI GPT-4o, Meta Llama-3-3-70B-Instruct, Anthropic Claude-3-5-Sonnet, and Mistral-Large-2411). The resulting 25,000 computer-generated stories were analyzed using a separate GPT-4-Turbo model instance to detect differences in how people are represented related to themes of bias described in previous literature. Results: Our findings reveal differences in how people are represented between story datasets with and without ID descriptors. These differences go beyond established characteristics of ID and imply the presence of mostly negative implicit biases. Identified differences related to considering people with ID as younger, with themes of paternalism and infantilization; depicting them as more inspirational and symbolic; as needing help more often, being dependent, and being saved; and having a negative perception of them and more hesitation to include them. Conclusions: These implicit biases are considered within the context of past discrimination towards people with ID and highlight the need for diligence against implicit bias towards people with ID in AI development. This research underscores the importance of assessing and mitigating implicit bias in decision-making technologies to prevent future societal harm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 51 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

15 of 51 references.

References · 15

  1. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  2. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  3. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  4. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  5. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 144
  6. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  7. 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
  8. 2024Are Large Language Models Capable of Generating Human-Level Narratives?cited by 79
  9. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  10. 2023LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Codingcited by 64
  11. 2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Modelscited by 33
  12. 2024Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluationcited by 32
3 more
  1. 2024Identifying and Improving Disability Bias in GPT-Based Resume Screeningcited by 28
  2. 2023Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytellingcited by 27
  3. 2021Intersectional Bias in Causal Language Modelscited by 24

Built on by

Not cited yet.