activity
20242026
most citedMitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging

1 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.CL2025

Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement

Xiaowei Yuan, Zhao Yang, Ziyang Huang +5

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet they often struggle with context-faithfulness generations that properly reflect context…