一作ACL 2026Findings· Findings of ACL
Q u C o- RAG : Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
Dehai Min · Kailin Zhang · Tongtong Wu · Lu Cheng
摘要
Dynamic Retrieval-Augmented Generation adaptively determines when to retrieve during generation to mitigate hallucinations in large language models (LLMs). However, existing methods rely on model-internal signals (e.g., logits, entropy), which are fundamentally unreliable because LLMs are typical...