3 papers
cs.CL2026
LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems
Zhipeng Song, Xiangyu Kong, Xinrui Bao +5
Large language models (LLMs) have revolutionized natural language processing, yet hallucinations in knowledge-intensive tasks remain a critical challenge. Retrieval-augmented gener…
cs.CL2026
Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection
Zhipeng Song, Yizhi Zhou, Xiangyu Kong +6
Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passage…
cs.LG2024
UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba
Li Wu, Wenbin Pei, Jiulong Jiao +1
Multivariate Time series forecasting is crucial in domains such as transportation, meteorology, and finance, especially for predicting extreme weather events. State-of-the-art meth…