2 papers
cs.LG2026
Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
Jaeseung Heo, J Rosser, Dongwoo Kim
Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influence different behaviors of an L…
cs.AI2026
Gradient Atoms: Unsupervised Discovery, Attribution and Steering of Model Behaviors via Sparse Decomposition of Training Gradients
J Rosser
Training data attribution (TDA) methods ask which training documents are responsible for a model behavior. However, models often learn broad concepts shared across many examples. M…