Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities
Summary
This arXiv paper investigates implicit bias in LLM-based chat AI toward people with intellectual disabilities by generating and analyzing 25,000 stories across five LLMs. Findings reveal negative biases such as infantilization, paternalism, and dependency, highlighting the need for bias mitigation in AI development.
View Cached Full Text
Cached at: 07/31/26, 04:01 AM
# Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities Source: [https://arxiv.org/abs/2607.26062](https://arxiv.org/abs/2607.26062) [View PDF](https://arxiv.org/pdf/2607.26062) > Abstract: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\. ## Submission history From: Karly Coffey \[[view email](https://arxiv.org/show-email/f6d209b6/2607.26062)\] **\[v1\]**Tue, 16 Jun 2026 20:30:06 UTC \(936 KB\)
Similar Articles
How User-AI Mistreatment Occurs and Matters in Conversational Systems?
This paper analyzes user-AI mistreatment in conversational systems by auditing LMSYS-Chat-1M conversations, revealing distinct patterns in hostility detection and its implications for AI safety and alignment.
Using LLMs
The article reflects on the limited use and understanding of LLMs such as ChatGPT among personal acquaintances, raising questions about widespread AI tool adoption.
AI is more likely than humans to form biases when hiring
New research shows that LLMs can develop their own biases from experience and stereotype job applicants more than humans, raising concerns about AI in hiring.
Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs
Investigates how large language models represent disability by simulating social media posts from the perspective of individuals with disabilities, finding that LLMs often produce overly positive stereotypes that fail to capture authentic experiences.
Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs
This paper audits how LLMs default to US or Chinese legal frameworks based on input language, finding a systematic bias where English prompts favor US answers and Chinese prompts favor China answers. The authors propose mitigations.