作者位次 #4/8ACL 2026Poster· Natural Language Processing
G en P rove: Learning to Generate Text with Fine-Grained Provenance
Jingxuan Wei · Xingyue Wang · Yanghaoyu Liao · Jie Dong · Yuchen Liu · Caijun jia · Bihui Yu · Junnan Zhu
摘要
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 supports a generated claim. Existing methods are typically coarse-grained and fail to distinguish between...