REVIEW 2 cited by
Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
LLM outputs fall sharply under small input perturbations when the input was memorized, and this sensitivity can be used to flag memorized content in black-box models.
-
ICL CIPHERS: Quantifying "Learning" in In-Context Learning via Substitution Ciphers
LLMs perform consistently better on tasks where input words are replaced with a consistent, reversible substitution cipher than when replacements are random, and the authors propose this gap as a measure of task learn...
Discussion (0). Continue with ORCID to comment.