Author

Maosong Sun

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jun 2025

KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG

KARE-RAG (Knowledge-Aware Refinement and Enhancement for RAG), a training-time scaffolded alignment framework that uses structured knowledge representations as temporary scaffolds to expose evidence organization, support localized factual refinement, and construct fine-grained preference pairs is presented.

Yongjian Li, Haocheng Chu, Yu-Kun Yan et al. · arXiv.org · 0 citations