# Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks

Source: [Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks](<https://www.sota2.com/research/paper/68fa746f1e209131cea61be4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:38:02.139Z

Authors: Verna Dankers, Ivan Titov

Published: 2024-08-09T09:30:57.000Z

## Abstract

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are questions that remain largely unanswered. Given a multi-layered neural model, where does memorisation occur in the millions of parameters? Related work reports conflicting findings: a dominant hypothesis based on image classification is that lower layers learn generalisable features and that deeper layers specialise and memorise. Work from NLP suggests this does not apply to language models, but has been mainly focused on memorisation of facts. We expand the scope of the localisation question to 12 natural language classification tasks and apply 4 memorisation localisation techniques. Our results indicate that memorisation is a gradual process rather than a localised one, establish that memorisation is task-dependent, and give nuance to the generalisation first, memorisation second hypothesis.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.04965>)

[PDF](<https://arxiv.org/pdf/2408.04965.pdf>)
