Step-Resolved Data Attribution for Looped Transformers
MCML Authors
David Mildenberger
Martin Menten
Dr.
JRG Leader AI for Vision
Abstract
David Mildenberger
Martin Menten
Dr.
JRG Leader AI for Vision
Abstract
We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for τ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all loop iterations, obscuring when during the recurrent computation a training example matters. We introduce textit{Step-Decomposed Influence (SDI)}, which decomposes TracIn into a length-τ influence trajectory by unrolling the recurrent computation graph and attributing influence to specific loop iterations. To make SDI practical at transformer scale, we propose a TensorSketch implementation that never materialises per-example gradients. Experiments on looped GPT-style models and algorithmic reasoning tasks show that SDI scales excellently, matches full-gradient baselines with low error and supports a broad range of data attribution and interpretability tasks with per-step insights into the latent reasoning process.
misc KMG+26
Preprint
Feb. 2026Authors
G. Kaissis • D. Mildenberger • J. Gomez • M. J. Menten • E. TriantafillouLinks
arXivResearch Area
BibTeXKey: KMG+26