评分 6 · 来源：cs.LG updates on arXiv.org · 发布于 2026-04-20
评分依据：RAGognizer: 通过检测头集成实现幻觉感知微调
要点
arXiv:2604.15945v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Nonetheless, current models still produce closed-domain hallucinations and generate content that is unsupported by the retrieved context. Current detection approaches typically treat hallucination as a post-hoc problem, relying on black-box consistency checks or probes over frozen internal representations. In this work, we demonstrate that hallucination detection based o…
🤖 AI 点评
本文提供了AI领域的重要信息，值得行业从业者关注。