2 papers
cs.IR2026
Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesis
Zheng Dou, Zhao Zhang, Hao Geng +2
Retrieval-augmented scientific synthesis aims to answer complex research questions by integrating information from multiple papers into comprehensive and well-grounded responses. S…
cs.AI2025
Dual-Difficulty Curriculum Learning for Direct Preference Optimization
Mengyang Li, Haozhan Geng, Zhong Zhang +1
Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dimensional view of difficulty. In t…