Skip to content

Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models

Sep 2026 · 0 citations · 31 references
Computer Science

TL;DR

This work takes a fine-grained look at memorization by decomposing the loss trajectory of memorized sequences over training and model parameters, finding that memorization in both cases is characterized by sequence-level gradient alignment.

Abstract

Memorization has been proposed as a mechanism to explain how language models fit the tail of their training distributions, but its training dynamics are not understood well. In this work, we take a fine-grained look at memorization by decomposing the loss trajectory of memorized sequences over training and model parameters. Across the Pythia family, we study memorization of duplicated training sequences (recitation) and rare ones (recollection). We find that memorization in both cases is characterized by sequence-level gradient alignment, though recitation suffers from misalignment with other training influences which causes forgetting, explaining the necessity for higher duplication of these examples. We further show that the lower model layers are the most involved in memorization and forgetting. Predicting memorization, our decomposition improves over a cross-entropy baseline, especially in larger models and early in training. Intervening on a small set of highly influential parameters we are able to ablate memorization in the final model. Together, these findings advance our understanding of how memorization develops during training and offer insights for predicting and intervening on it.

View source

Similar papers

#artificial intelligence Review Aug 2026

When to Review: Spaced Repetition for Continual Pre-Training of Language Models

Spaced Repetition Training (SRT) is introduced, a continual learning framework inspired by cognitive science, which schedules sample-rehearsal using the SuperMemo-2 (SM-2) algorithm, and preserves broad benchmark performance that naive continual pre-training and uniform replay substantially degrade.

Alankar Atreya, Devesh Batra, Yoages Kumar Mantri et al. · 1 citation
#artificial intelligence Open access Sep 2026

Memory vs. Context? Influential Factors of Factual Recall in Language Models

We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradictory in-context statements. We replicate their world-capitals experiments on 31 models spanning Pythia, GPT-2, Qwen3, and Ministral families, including base and post-t...

Guilhem Fouilhé, Nicholas Asher, Philippe Muller · 0 citations

On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models

It is shown that this gating mechanism causes SSMs to first learn an in-weights"memorization"solution, while delaying, or even preventing, convergence to a correct in-context learning solution, and that gating is often beneficial for improving generalization to long sequence lengths.

W. Tong, Aryo Lotfi, Emmanuel Abbé et al. · 1 citation
#artificial intelligence Preprint Oct 2026

How Learning Governs Unlearning across the Memorization-Generalization Spectrum

This paper first classify memorization- and generalization-heavy models using grokking in modular addition and compare their responses to unlearning, showing that the latter suffer greater retain damage, i.e., a larger performance drop on the retain set.

Hwiyeong Lee, H. Lim, Ingyu Bang et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.