#natural language process...
Oct 2025
CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models
A two-stage framework that derives lightweight scope guidance before aspect refinement and summarization, improving focus and reducing over-generation is introduced, establishing a crucial insight for the deployment of LLMs in similar real-world applications.
Yong-En Tian, Yu-Chien Tang, An-Zi Yen et al.
· arXiv.org · 0 citations