We draw attention to the final-model-only setting for training data attribution, propose a further training gold standard for it, and show how various gradient-based methods approximate further training.

This paper introduces distributional training data attribution, a data attribution framework that accounts for stochasticity in deep learning training, enabling a mathematical justification for why influence functions work in this setting.

AirRep is a text representation model optimized for TDA, offering performance comparable to gradient-based methods while being significantly more efficient.