AI ethics evidence index Search
Source-linked daily record
Evidence record 3712 · automatically gathered

Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication

Safety alignment reduces explicitly harmful outputs but inadvertently encodes a sanitized, neuronormative representation of marginalized communication. We investigate this encoding using a dual-persona rewrite paradigm, prompting ten large language models (LLMs) to rewrite naturally occurring autistic discourse from either an autistic or neurotypical persona. We uncover autistic-persona rewrites diverge significantly more in lexical form and affective register than neurotypical rewrites, despite

Record details

Published: 26 May 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Safety & alignment · Finance, VC & PE
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Representation Alignment Rests on Linear Structure

arXiv · 22 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation

arXiv · 8 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

arXiv · 14 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology

arXiv · 5 March 2026

Shared topic: Safety & alignment · Shared topic: Finance, VC & PE

Curriculum Learning for Safety Alignment

arXiv · 25 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

DeGRe: Dense-supervised Generative Reranking for Recommendation

arXiv · 25 May 2026

How to cite this record

ethics.ai (26 May 2026), “Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication,” evidence record 3712, https://ethics.ai/record/3712 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.