arXiv cs.CLPaper
Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison
This is a serious finding: RLVR training for correct answers does not buy citation faithfulness, and the unfaithful citation rate is quantified at scale. If your RAG system is user-facing and cites sources, this says you cannot rely on reward-based training to fix false attribution. Citation accuracy needs explicit measurement and training.