Efficient Retrieval of Influential LLM Training Examples

Attributing LLM outputs to the training examples that causally influence their behavior can give us visibility into LLMs’ opaque reasoning and help us understand subtle persona changes. Unfortunately, finding training data attribution algorithms which are both accurate and scalable has remained an elusive goal. I argue for separately studying an Estimation Problem (accurately estimating the causal effect of a training example) and a Retrieval Problem (efficiently finding the highest-scoring training examples). I then present a generic retrieval method for influential sequences which can be paired with a wide range of influence estimators (including EKFAC) and for which one can obtain high confidence about recall. I discuss how causal training data attribution can be used as a tool to assure LLM alignment.