RetroThinker: Enabling Retrospective Thinking in Speech LLMs
Speech large language models (SpeechLLMs) offer reduced latency and retain paralinguistic nuances that are typically lost in cascaded automatic speech recognition (ASR) and text-based LM architectures. However, they continue to lag behind text-only LLMs on complex reasoning tasks, while real-time spoken interaction imposes strict latency constraints. Although prior works employ Chain-of-Thought…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
