4 papers · 1 filter
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
Shrestha Datta, Hongfu Liu, Anshuman Chhabra
Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adju…
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Shrestha Datta, Hongfu Liu, Anshuman Chhabra
Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs.…
What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis
Shahriar Kabir Nahin, Wenxiao Xiao, Joshua Liu +2
Data-centric learning seeks to improve model performance from the perspective of data quality, and has been drawing increasing attention in the machine learning community. Among it…
Salutary Labeling with Zero Human Annotation
Wenxiao Xiao, Hongfu Liu
Active learning strategically selects informative unlabeled data points and queries their ground truth labels for model training. The prevailing assumption underlying this machine…