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 which examples require memorisation and where in the millions (or billions) of parameters memorisation occurs are questions that remain largely unanswered.
In this talk, I first elaborate on the localisation question by examining memorisation in the context of classification in fine-tuned PLMs, using 12 tasks. Our findings give nuance to the generalisation-first memorisation-second hypothesis dominant in the literature and find memorisation to be a gradual process rather than a localised one.
Secondly, I discuss memorisation from the viewpoint of the data using neural machine translation (NMT) models by putting individual data points on a memorisation-generalisation map.
I illustrate how the data points' characteristics are predictive of memorisation in NMT and describe the influence that subsets of that map have on NMT systems' performance.
The talk is based on the following two publications:
Dankers, V., & Titov, I. (2024). Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks. ACL-Findings
Dankers, V., Titov, I., & Hupkes, D. (2023). Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation. EMNLP
