# Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?

arXiv: https://arxiv.org/abs/2610.13550 · HTML: https://mlsanity.com/paper/2610.13550/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 30 of 39)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words](https://mlsanity.com/paper/2406.13340/) (2024)
- [DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment](https://mlsanity.com/paper/2507.02768/) (2025)
- [SD-QA: Spoken Dialectal Question Answering for the Real World](https://mlsanity.com/paper/2109.12072/) (2021)
- [Stereotype or Personalization? User Identity Biases Chatbot Recommendations](https://mlsanity.com/paper/2410.05613/) (2024)
- [Social Bias Probing: Fairness Benchmarking for Language Models](https://mlsanity.com/paper/2311.09090/) (2023)
- [Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps](https://mlsanity.com/paper/2402.17954/) (2024)
- [ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction](https://mlsanity.com/paper/2511.08723/) (2025)
- [Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models](https://mlsanity.com/paper/2407.06957/) (2024)
- [Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition](https://mlsanity.com/paper/2406.05065/) (2024)
- [Evaluating Gender Bias in Speech Translation](https://mlsanity.com/paper/2010.14465/) (2020)
- [Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music](https://mlsanity.com/paper/2604.10905/) (2026)
- [Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning](https://mlsanity.com/paper/2103.05834/) (2021)
- [Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models](https://mlsanity.com/paper/2408.07665/) (2024)
- [A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems](https://mlsanity.com/paper/2204.01397/) (2022)
- [LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models](https://mlsanity.com/paper/2308.10390/) (2023)
- [EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models](https://mlsanity.com/paper/2510.22758/) (2025)

## Abstract (arXiv)

Recent speech LLMs can leverage rich paralinguistic cues, enabling more complex and personalized interactions. However, little work investigates how this sensitivity can lead to stereotyping, and existing evaluations largely measure demographic disparities without distinguishing beneficial personalization from stereotypical behavior. We introduce BASIS-Bench, a benchmark designed to disentangle these two aspects through three axes: (1) demographic robustness, measuring disparities in content-based tasks across speakers and demographic classification capabilities; (2) stereotypical bias, measuring whether perceived demographic cues trigger unprompted stereotypical behavior; and (3) personalization, measuring whether models can tailor responses to demographic characteristics when explicitly requested. We evaluate eight recent speech LLMs and find that, despite often recognizing demographic cues, most fail to translate them into appropriate personalization. Explicit demographic labels improve personalization but also amplify stereotypical associations already present in the textual backbones. These findings highlight the need to train speech LLMs not only to perceive demographic cues, but to learn when they should shape their responses.