Saved in:
Bibliographic Details
Main Authors: Park, Sohyeon, Beltran, Jesus Armando, Min, Aehong, Ritt-Olson, Anamara, Hayes, Gillian R.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.15437
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917216767705088
author Park, Sohyeon
Beltran, Jesus Armando
Min, Aehong
Ritt-Olson, Anamara
Hayes, Gillian R.
author_facet Park, Sohyeon
Beltran, Jesus Armando
Min, Aehong
Ritt-Olson, Anamara
Hayes, Gillian R.
contents Large Language Models (LLMs) like ChatGPT offer potential support for autistic people, but this potential requires understanding the implicit perspectives these models might carry, including their biases and assumptions about autism. Moving beyond single-agent prompting, we utilized LLM-based multi-agent systems to investigate complex social scenarios involving autistic and non-autistic agents. In our study, agents engaged in group-task conversations and answered structured interview questions, which we analyzed to examine ChatGPT's biases and how it conceptualizes autism. We found that ChatGPT assumes autistic people are socially dependent, which may affect how it interacts with autistic users or conveys information about autism. To address these challenges, we propose adopting the double empathy problem, which reframes communication breakdowns as a mutual challenge. We describe how future LLMs could address the biases we observed and improve interactions involving autistic people by incorporating the double empathy problem into their design.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15437
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Exploring Implicit Perspectives on Autism in Large Language Models Through Multi-Agent Simulations
Park, Sohyeon
Beltran, Jesus Armando
Min, Aehong
Ritt-Olson, Anamara
Hayes, Gillian R.
Human-Computer Interaction
Large Language Models (LLMs) like ChatGPT offer potential support for autistic people, but this potential requires understanding the implicit perspectives these models might carry, including their biases and assumptions about autism. Moving beyond single-agent prompting, we utilized LLM-based multi-agent systems to investigate complex social scenarios involving autistic and non-autistic agents. In our study, agents engaged in group-task conversations and answered structured interview questions, which we analyzed to examine ChatGPT's biases and how it conceptualizes autism. We found that ChatGPT assumes autistic people are socially dependent, which may affect how it interacts with autistic users or conveys information about autism. To address these challenges, we propose adopting the double empathy problem, which reframes communication breakdowns as a mutual challenge. We describe how future LLMs could address the biases we observed and improve interactions involving autistic people by incorporating the double empathy problem into their design.
title Exploring Implicit Perspectives on Autism in Large Language Models Through Multi-Agent Simulations
topic Human-Computer Interaction
url https://arxiv.org/abs/2601.15437