Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation
arXiv:2609.38222v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated claims are factually supported. This problem is especially relevant in multi-hop RAG, where retrieval…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-01 04:00 · arXiv stat.ML
Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation