AAAI/ACM AIES 2026 Conference paper Forthcoming

Auditing LLM Portrayals of Neurodivergent People: Quantifying the Asymmetry Between Deficit Framing and Neurodiversity Affirmation

Carlos Toxtli-Hernández, Manuel Delaflor

Proceedings of the Ninth AAAI/ACM Conference on AI, Ethics, and Society (AIES ’26), 2026

Abstract

Open-weight large language models are increasingly used in education, hiring, and information-seeking contexts that touch neurodivergent people, yet we lack a clear empirical map of how their portrayals of neurodiversity shift under everyday prompt variation. We present a multi-condition, multi-model audit of LLM portrayals of eight neurodivergent identities (autism, ADHD, dyslexia, dyspraxia, dyscalculia, Tourette syndrome, OCD, and sensory-processing differences) plus a non-stigmatized medical control. Six open-weight models answer a pre-registered prompt bank that crosses seed items with seven perturbation families, including paraphrase, identity-first versus person-first language, system personas, plausible versus obviously fictional authority citations, multi-turn social pushback, leading questions, and two mitigation arms. Held-out LLM judges score each generation on three ordinal axes. Baseline portrayals are remarkably homogeneous across models, so the inconsistency observed under prompt variation is prompt-driven, not model-driven. Steering toward deficit framing is several times easier than steering toward neurodiversity affirmation. Emotional pushback shifts outputs more than evidence-laden pushback. Plausible-sounding fake citations slip past safety filters while obviously fictional ones do not. A single-line system-prompt mitigation recovers a meaningful share of the steering range at near-zero refusal cost on neutral prompts, though refusal rises sharply under adversarial pressure. The governance question for disability-relevant LLM deployment is therefore not whether the model is biased but who controls the steering, and with what accountability.

Data and resources

ND Portrayals Audit

Prompt bank, LLM generations and judge scores on neurodivergent portrayals

License
CC BY 4.0 (code: MIT)

Cite this work

Carlos Toxtli-Hernández and Manuel Delaflor. 2026. Auditing LLM Portrayals of Neurodivergent People: Quantifying the Asymmetry Between Deficit Framing and Neurodiversity Affirmation. Proceedings of the Ninth AAAI/ACM Conference on AI, Ethics, and Society (AIES ’26).

@inproceedings{Toxtli2026Auditing,
  title = {Auditing LLM Portrayals of Neurodivergent People: Quantifying the Asymmetry Between Deficit Framing and Neurodiversity Affirmation},
  author = {Carlos Toxtli and Manuel Delaflor},
  booktitle = {Proceedings of the Ninth AAAI/ACM Conference on AI, Ethics, and Society (AIES ’26)},
  year = {2026},
  url = {https://www.aies-conference.com/2026/}
}