Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
Zhihang Yuan, Chengyu Yue, Long Huang +2
Instruction tuning is a standard paradigm for adapting large language models (LLMs), but modern instruction datasets are large, noisy, and redundant, making full-data fine-tuning c…
cs.CL2025
Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documents
Long Huang, Ming Zhao, Limin Xiao +2
The 3rd Generation Partnership Project (3GPP) documents is key standards in global telecommunications, while posing significant challenges for engineers and researchers in the tele…