作者位次 #4/5SIGIR 2026Poster· Information Retrieval (Industry)
Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
Xunzhuo Liu · Bowei He · Xue Liu · Haichen Zhang · Huamin Chen
摘要
Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large langu...