arXiv cs.CL· Adnan Al Ali, Jind\v{r}ich Libovick\'y, Anne Lauscher·· 2 天前AI 评分22
通过对抗训练与蒸馏方法缓解音频大语言模型的偏见
Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods
AI 导读
研究针对音频大语言模型（AuLLMs）的性别偏见，用对抗方法让模型"遗忘"性别感知，且在其他基准任务上性能不降。作者进一步蒸馏出性别无关模型，使其能感知性别但响应与教师模型一致，除非被显式触发。方法在三个 AuLLMs 上测试，性别遗忘部分结果令人满意，蒸馏部分仅部分满意。
正文 · 原文
Abstract:Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcription. This expands the model's accessibility and capabilities by encoding non-verbal cues. However, using non-verbal cues may lead to biased behaviour based on the attributes inferred (or assumed) from them. In this work, we focus on the gender attribute and show that models' perception of it can be unlearned using adversarial methods without a loss in performance on other benchmarked tasks. Such models are useful in situations where gender inference is unwanted. However, in other practical settings, gender perception (without bias) may be this http URL a less radical measure, we distil the gender-agnostic model, creating a model that perceives gender but responds similarly to the gender-agnostic teacher, unless explicitly this http URL apply our newly proposed methods to three AuLLMs and obtain satisfactory results in the gender-unlearning part and partially satisfactory results in the distilling part.
| Comments: | Submitted to ARR (October 2026) |
| Subjects: | Computation and Language (cs.CL); Sound (cs.SD) |
| Cite as: | arXiv:2610.21763 [cs.CL] |
| (or arXiv:2610.21763v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21763 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Adnan Al Ali [view email]
[v1]
Thu, 15 Oct 2026 12:19:47 UTC (198 KB)
来源：arXiv cs.CL · arxiv.org