3 papers
cs.LG2026
Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs
Beier Luo, Cheng Wang, Hongxin Wei +2
Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-tr…
cs.CL2025
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
Youan Cong, Pritom Saha Akash, Cheng Wang +1
We introduce the \textit{Extract-Refine-Retrieve-Read} (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RA…
cs.CR2025
Dataset Ownership in the Era of Large Language Models
Kun Li, Cheng Wang, Minghui Xu +2
As datasets become critical assets in modern machine learning systems, ensuring robust copyright protection has emerged as an urgent challenge. Traditional legal mechanisms often f…