# Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs

arXiv: https://arxiv.org/abs/2609.38106 · HTML: https://mlsanity.com/paper/2609.38106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Characterising Bias in Compressed Models](https://mlsanity.com/paper/2010.03058/) (2020)
- [Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression](https://mlsanity.com/paper/2403.15447/) (2024)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [Pruning has a disparate impact on model accuracy](https://mlsanity.com/paper/2205.13574/) (2022)
- [The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR](https://mlsanity.com/paper/2303.18110/) (2023)
- [Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression](https://mlsanity.com/paper/2407.04965/) (2024)
- [Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults](https://mlsanity.com/paper/2309.07927/) (2023)
- [On the social bias of speech self-supervised models](https://mlsanity.com/paper/2406.04997/) (2024)
- [On Fairness of Low-Rank Adaptation of Large Models](https://mlsanity.com/paper/2405.17512/) (2024)
- [BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models](https://mlsanity.com/paper/2408.04556/) (2024)
- [Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN Corpus](https://mlsanity.com/paper/2502.17284/) (2025)
- [Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition](https://mlsanity.com/paper/2604.21276/) (2026)
- [Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries](https://mlsanity.com/paper/2601.18899/) (2026)
- [On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR](https://mlsanity.com/paper/2603.27981/) (2026)

## Abstract (arXiv)

Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggregate word error rate (WER), which can hide how pruning affects different demographic groups. In this work, we systematically study the effect of audio encoder pruning on SLAM-ASR for different demographic groups. Using the Fair-Speech and Common Voice datasets, we found that the pruning does not affect all demographic groups equally; the gap between best- and worst-performing groups increases in fold. These disparities appear across all three encoder scales, but only the largest model initially hides them behind aggregate WER. LoRA adaptation improves WER for every group, but benefits groups already performing well more strongly and widens for certain groups. On Common Voice English, Danish, and Dutch, accent gaps persist but do not clearly widen, showing that the fairness effects of pruning vary across datasets and must be measured directly. Our findings suggest that for pruned models, deployment decisions should include per-group WER, with the worst-performing group's error rate as an explicit criterion.