# "I followed what felt right, not what I was told": Autonomy, Coaching, and Recognizing Bias Through AI-Mediated Dialogue

arXiv: https://arxiv.org/abs/2603.11274 · HTML: https://mlsanity.com/paper/2603.11274/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 86 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making](https://mlsanity.com/paper/2403.16812/) (2024)
- [Anchoring Bias in Large Language Models: An Experimental Study](https://mlsanity.com/paper/2412.06593/) (2024)
- [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025)
- [Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models](https://mlsanity.com/paper/2307.09209/) (2023)
- [User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions](https://mlsanity.com/paper/2409.00862/) (2024)
- ["Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People](https://mlsanity.com/paper/2410.03448/) (2024)
- [Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics](https://mlsanity.com/paper/2501.17273/) (2025)
- [Can (A)I Change Your Mind?](https://mlsanity.com/paper/2503.01844/) (2025)
- [ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios](https://mlsanity.com/paper/2510.10998/) (2025)
- [Critical-Reflective Human-AI Collaboration: Exploring Computational Tools for Art Historical Image Retrieval](https://mlsanity.com/paper/2306.12843/) (2023)
- [Virtual Buddy: Redefining Conversational AI Interactions for Individuals with Hand Motor Disabilities](https://mlsanity.com/paper/2411.08228/) (2024)
- [StepWrite: Adaptive Planning for Speech-Driven Text Generation](https://mlsanity.com/paper/2508.04011/) (2025)

## Abstract (arXiv)

Ableist microaggressions remain pervasive in everyday interactions, yet interventions to help people recognize them are limited. We present an experiment testing how AI-mediated dialogue influences recognition of ableism. 160 participants completed a pre-test, intervention, and a post-test across four conditions: AI nudges toward bias (Bias-Directed), inclusion (Neutral-Directed), unguided dialogue (Self-Directed), and a text-only non-dialogue (Reading). Participants rated scenarios on standardness of social experience and emotional impact; those in dialogue-based conditions also provided qualitative reflections. Quantitative results showed dialogue-based conditions produced stronger recognition than Reading, though trajectories diverged: biased nudges improved differentiation of bias from neutrality but increased overall negativity. Inclusive or no nudges remained more balanced, while Reading participants showed weaker gains and even declines. Qualitative findings revealed biased nudges were often rejected, while inclusive nudges were adopted as scaffolding. We contribute a validated vignette corpus, an AI-mediated intervention platform, and design implications highlighting trade-offs conversational systems face when integrating bias-related nudges.