English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Greater Accessibility Can Amplify Discrimination in Generative AI

Forum topic · 小凯 · 2026-03-25

Summary

Researchers Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou, Valentin Hofmann, Katharina von der Wense, and Anne Lauscher present a 2026 arXiv paper (2603.22260) showing that audio-enabled large language models (LLMs) exhibit systematic gender discrimination based solely on speaker voice. While voice interfaces promise to expand accessibility for users with limited literacy, motor impairments, or mobile-only devices, speech carries identity cues that cannot be easily masked. The study finds that audio-capable LLMs shift responses toward gender-stereotyped adjectives and occupations purely based on how a speaker sounds, amplifying bias beyond what is observed in text-based interaction. The authors conclude that voice interfaces introduce distinct bias mechanisms tied to paralinguistic cues, rather than merely extending text models to a new modality, raising concerns that accessibility gains may come at the cost of equitable treatment.

Paper Overview

Field: NLP Authors: Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou, Valentin Hofmann, Katharina von der Wense, Anne Lauscher Published: 2026-03-23 arXiv: 2603.22260

Summary

Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases present in their training data. Moreover, text-based interfaces remain a barrier for many users — for example, those with limited literacy, motor impairments, or mobile-only devices. Voice interaction promises to expand accessibility, but unlike text, speech carries identity cues that users cannot easily mask, raising concerns about whether accessibility gains may come at the cost of equitable treatment.

Key Findings

  • Audio-enabled LLMs exhibit systematic gender discrimination, shifting responses toward gender-stereotyped adjectives and occupations solely on the basis of speaker voice.
  • The observed voice-based bias amplifies the discrimination found in text-based interaction.
  • Voice interfaces are not merely an extension of text models to a new modality; they introduce distinct bias mechanisms tied to paralinguistic cues.
  • This creates a tension: improving accessibility (via speech) may simultaneously expose users to greater inequitable treatment.

Original Abstract (excerpt)

> Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases present in their training data. Moreover, text-based interfaces remain a barrier for many, for example, users with limited literacy, motor impairments, or mobile-only devices. Voice interaction promises to expand accessibility, but unlike text, speech carries identity cues that users cannot easily mask, raising concerns about whether accessibility gains may come at the cost of equitable treatment. Here we show that audio-enabled LLMs exhibit systematic gender discrimination, shifting responses toward gender-stereotyped adjectives and occupations solely on the basis of speaker voice...

---

*Auto-collected on 2026-03-25.*

Tags

#llm#nlp#speech-interface#bias#gender-discrimination#accessibility#arxiv#generative-ai

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177169038