Towards Quantifying Benchmark Optimization in ASR Models
- 类型：arxiv
- 标识：2608.19936
- 链接：https://arxiv.org/abs/2608.19936
- 主分类：evaluation
- 形态：benchmark
- 被引：0
- 被引来源：Semantic Scholar
- S2被引：0
- 影响力被引：0
- TLDR：This work presents a methodology for quantifying benchmark optimization, focusing on cases where the audio underdetermines the reference transcript, and indicates that high-performing models exhibit benchmark-conditioned behaviors that can inflate benchmark performance without reflecting improved general-purpose transcription ability.
- 副分类：multimodal
- 待LLM分类：否
- 标题中文：迈向 ASR 模型中基准过拟合的量化
- TLDR中文：本文提出一种量化基准优化的方法论，聚焦于音频对参考转写不充分确定的情形，指出高性能模型会表现出基准条件化行为，从而虚高基准得分，却未必反映通用转写能力的真正提升。
- 来源文件：
- /inbox/tom/_candidates/2026-08-21-agent-rag-longcontext-candidates.json
- [S2 enrich]