语音大语言模型适应中的训练种子可变性
一项研究发现，训练种子的可变性对语音大语言模型中的公平性指标有显著影响，比音频压缩因素的影响更为显著。
01
证据
- AarXiv cs.CL研究机构2026-10-02 12:00
At 460 h of clean LibriSpeech, the seed moves fairness metrics more than compression does on most demographic axes.
- AarXiv cs.CL研究机构2026-10-02 12:00
We fine-tune the Q-former projector and LoRA adapters of a speech LLM at five audio compression factors and six random seeds
- AarXiv cs.CL研究机构2026-10-02 12:00
Abstract: Demographic fairness gaps in automatic speech recognition are almost always reported from a single training run. We fine-tune the Q-former projector…