cs.CLOct 29, 2026

Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation

Authors: Aryan Chowdhury, Riza Batista-Navarro

Organizations: University of Manchester

Abstract

Large language models have been shown to memorise and reproduce verbatim sequences from their training data, raising concerns about privacy leakage, intellectual property exposure, and the limits of generalisation. Recent theoretical work suggests that attention heads may contribute to this behaviour by functioning as associative memory mechanisms, with memorisation capacity scaling with the number of heads. At the same time, empirical work has shown that many attention heads are redundant and can be pruned with limited impact on downstream performance. Despite these parallel findings, the effect of pruning redundant heads on memorised-sequence reproduction remains unexplored. In this work, we demonstrate that zeroing out a substantial fraction of attention heads prior to inference can significantly suppress verbatim memorisation while preserving, or even improving, language modelling performance on the benchmark used to identify redundant heads. Evaluating GPT-2-XL(1.5B) on known memorised sequences, we find that pruning 729 task-redundant heads reduces the memorisation count by 91.5%, while improving WikiText-103 perplexity by 0.92. These findings suggest that attention-head redundancy can be exploited to mitigate memorisation at inference time, without retraining or modifying the training data.

Figures & tables

Explore similar work

Jan 11, 2026

Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning

Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant has remained elusive. In this work, we identify the BOS sink phenomenon as a key mechanism driving this layer-wise sensitivity. We show that attention heads with high BOS sink scores are strongly associated with functional redundancy: such heads, especially in deeper layers, contribute little to predictive performance and effectively serve as dumping grounds for superfluous attention weights. Leveraging this insight, we introduce a simple pruning strategy that removes high-BOS sink heads. Experiments on Gemma-3, Llama-3.1, and Qwen3 demonstrate that this approach identifies redundant transformer components more reliably than weight- and activation-based criteria in terms of downstream task retention, remaining close to dense baselines at low-to-moderate pruning ratios. We further find that high-scoring sink heads sustain their focus on BOS as context length grows. Overall, our results suggest that structural properties of attention offer a more direct basis for model compression than magnitude-based methods.
Sep 28, 2026

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

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.
Feb 9, 2026

Mitigating Memorization Where It Happens

Large language models (LLMs) can memorize and reproduce training sequences verbatim, raising privacy and copyright concerns. Existing mitigation methods apply interventions uniformly, often degrading predictions at the many positions unrelated to verbatim recall. We study a token-level log-likelihood ratio between a target model and a domain-competent reference with lower exposure to the evaluated sequences. Exposure-controlled experiments support its use for localizing positions associated with sequence-level verbatim recall. Across evaluated settings, a minority of positions carries a disproportionate share of the positive signal, motivating selective activation correction. From a first-order surrogate of the memorization-reduction objective, we derive a probe-steer framework, which decomposes intervention into a probe that flags high-signal activations and a steer that applies a correction only when the probe exceeds a threshold. We propose Gated Subspace Steering (GSS) as its practical instantiation: under a background normalization constraint, the probe-steer pairs that are optimal for this surrogate follow in closed form from the leading singular vectors of a whitened gradient-weighted activation matrix. Across four benchmarks, GSS achieves memorization suppression comparable to strong baselines, with favorable utility trade-offs in several settings, while requiring 10-100×\times less compute than optimization-based alternatives. Code is available at https://github.com/ubc-tea/Mitigating-Memorization-Where-It-Happens.