“It’s the only thing I can trust”: Envisioning Large Language Model Use by Autistic Workers for Communication Assistance

2024-03-05

International Conference on Human Factors in Computing Systems

AI Summary

This study investigates the applicability, opportunities, and risks of large language models (LLMs) as workplace social communication aids for autistic adults. Employing GPT-4 in a human–AI comparative experimental design (LLM vs. disguised human advisor), complemented by qualitative interviews with 11 autistic adult participants and expert review by vocational coaches, the research identifies a significant cognitive divergence: participants exhibited high trust and strong preference for LLM-generated advice, whereas employment coaches raised concerns regarding normative biases and insufficient contextual adaptation. The findings yield autism-centered design principles that prioritize user autonomy while integrating professional safety guardrails—balancing adaptive support with ethical accountability. This work establishes the first empirical foundation for developing AI-assisted tools tailored to neurodiverse populations, offering both a theoretical framework and actionable guidelines for inclusive, evidence-informed AI design in vocational contexts.

Technology Category

• Humans and AI: AI for Accessibility
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Autistic adults often experience stigma and discrimination at work, leading them to seek social communication support from coworkers, friends, and family despite emotional risks. Large language models (LLMs) are increasingly considered an alternative. In this work, we investigate the phenomenon of LLM use by autistic adults at work and explore opportunities and risks of LLMs as a source of social communication advice. We asked 11 autistic participants to present questions about their own workplace-related social difficulties to (1) a GPT-4-based chatbot and (2) a disguised human confederate. Our evaluation shows that participants strongly preferred LLM over confederate interactions. However, a coach specializing in supporting autistic job-seekers raised concerns that the LLM was dispensing questionable advice. We highlight how this divergence in participant and practitioner attitudes reflects existing schisms in HCI on the relative privileging of end-user wants versus normative good and propose design considerations for LLMs to center autistic experiences.

Problem

• Autistic workers face workplace stigma and seek communication support
• Large language models offer alternative social communication advice for autistic adults
• Divergence exists between user preference and professional concerns over LLM advice

Innovation

• Using GPT-4 chatbot for autistic workplace communication
• Comparing LLM advice with human confederate feedback
• Designing LLMs to prioritize autistic user experiences