Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment
基于评分标准的语音大模型多维度多评分者二语阅读语音评估
专题命中 幻觉与事实性 :alignment(abstract);trustworthy(abstract);分类 cs.CL、cs.AI
AI总结 本文提出基于评分标准的语音大模型微调方法,通过多维度评分标准和不确定性校准,提升二语阅读语音评估的可靠性与可解释性。
Comments Accepted to LREC 2026. This publication is part of the project Responsible AI for Voice Diagnostics (RAIVD) with file number NGF.1607.22.013 of the research programme NGF AiNed Fellowship Grants, which is financed by the Dutch Research Council (NWO)