Pith. sign in

REVIEW 3 cited by

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

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

arxiv 2406.17746 v2 pith:6LDABG62 submitted 2024-06-25 cs.CL cs.AI

classification cs.CLcs.AI
keywords memorizationmodelfactorssequencesphenomenonpredictivetaxonomyanalyzing
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the model and corpus. To build intuition around these factors, we break memorization down into a taxonomy: recitation of highly duplicated sequences, reconstruction of inherently predictable sequences, and recollection of sequences that are neither. We demonstrate the usefulness of our taxonomy by using it to construct a predictive model for memorization. By analyzing dependencies and inspecting the weights of the predictive model, we find that different factors influence the likelihood of memorization differently depending on the taxonomic category.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data

    cs.LG 2026-06 conditional novelty 6.0 of 10

    A model-agnostic audit detects synthetic data disclosures via feature-match and membership-inference tests that separate true from phantom leaks and give empirical differential-privacy lower bounds.

  2. Low-Perplexity LLM-Generated Sequences and Where To Find Them

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Only about 40% of low-perplexity 6-token spans generated by Pythia-6.9B can be exactly matched to The Pile, and the authors categorize matched and unmatched spans into four classes.

  3. Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy

    cs.SE 2026-07 conditional novelty 4.0 of 10

    A 7-billion-parameter coding model with multi-sampling matches a 32-billion-parameter model on repository-level completion under the same time budget, and compiler-error feedback improves pass rates across all models tested.

Pith tools