Machine Unlearning for Speech Question Answering in Large Audio-Language Models

Abstract

Large Audio-Language Models (LALMs) have recently shown strong capabilities in speech understanding and question answering (QA), but they also inherit privacy risks from large-scale training data, including the unintended memorization of sensitive information. In this work, we study machine unlearning for speech QA in LALMs, a setting that is more challenging than prior work on text-based Large Language Models (LLMs) or Automatic Speech Recognition (ASR) due to the tight coupling between acousti

Categories

Framework mappings

Suggested from the entry's categories.

@misc{liu2026machine,
  title = {{Machine Unlearning for Speech Question Answering in Large Audio-Language Models}},
  author = {Zhe Liu},
  year = {2026},
  month = sep,
  eprint = {2609.13195},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.13195}
}