Step-resolved data attribution for looped transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kaissis, Georgios, Mildenberger, David, Gomez, Juan Felipe, Menten, Martin J., Triantafillou, Eleni
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915789128335360
author Kaissis, Georgios
Mildenberger, David
Gomez, Juan Felipe
Menten, Martin J.
Triantafillou, Eleni
author_facet Kaissis, Georgios
Mildenberger, David
Gomez, Juan Felipe
Menten, Martin J.
Triantafillou, Eleni
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_10097
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Step-resolved data attribution for looped transformers
Kaissis, Georgios
Mildenberger, David
Gomez, Juan Felipe
Menten, Martin J.
Triantafillou, Eleni
Machine Learning
Artificial Intelligence
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.
title Step-resolved data attribution for looped transformers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.10097