AI RESEARCH
GenProve: Learning to Generate Text with Fine-Grained Provenance
arXiv CS.CL
•
ArXi:2601.04932v2 Announce Type: replace Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a cited source s a generated claim. Existing methods are typically coarse-grained and fail to distinguish between direct quotes and complex reasoning. In this paper, we