FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations

ArXi:2606.02615v1 Announce Type: cross Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. However, most auditory large language models are not explicitly trained to perform inference in this nstration-conditioned format, limiting the extent to which they can benefit from few-shot prompting. To address this limitation, we