Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs

ArXi:2604.08003v1 Announce Type: cross Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a dominant paradigm. Although recent LLM-based ASR models have shown promising performance on public benchmarks, it remains challenging to balance recognition quality with latency and overhead, while hallucinations further limit real-world deployment. In this study, we revisit LLM-based ASR from an entropy allocation perspective and