SOURCE-LINKED INTELLIGENCE

Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either externally through logit fusion or internally through warm initialization. However, how to effectively combine these two strategies remains underexplored. In this work, we refine warm-initialized LLM-based ASR models by leveraging their own pre-adaptation base LLMs, focusing on LoRA-adapted settings where the base LLM is preserved. To achieve this, we propose Hybrid Search, a targeted correction strategy motivated by two observations. First, interac

Read original source ↗ Open in workspace

recordType

paper

region

Global