REVIEW 4 cited by
Counterfactual Memorization in Neural Language Models
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
read the original abstract
Modern neural language models that are widely used in various NLP tasks risk memorizing sensitive information from their training data. Understanding this memorization is important in real world applications and also from a learning-theoretical perspective. An open question in previous studies of language model memorization is how to filter out "common" memorization. In fact, most memorization criteria strongly correlate with the number of occurrences in the training set, capturing memorized familiar phrases, public knowledge, templated texts, or other repeated data. We formulate a notion of counterfactual memorization which characterizes how a model's predictions change if a particular document is omitted during training. We identify and study counterfactually-memorized training examples in standard text datasets. We estimate the influence of each memorized training example on the validation set and on generated texts, showing how this can provide direct evidence of the source of memorization at test time.
Forward citations
Cited by 4 Pith papers
-
Bridging Compute- and Data-Optimal Pretraining
Pretraining loss obeys a single law in which repeated or paraphrased tokens count as η(N, data-per-parameter, expansion-ratio) fresh tokens, with total effective data saturating as derived tokens grow.
-
Rethinking Memorization Measures and their Implications in Large Language Models
Contextual memorization, defined by comparing a string's training loss against the best loss without training on that string, is stricter than counterfactual memorization and suggests that zero-memorization optimal le...
-
How much do language models memorize?
A compression-based measurement puts GPT-style model memorization capacity at roughly 3.6 bits per parameter, with membership inference success following a sigmoid in the dataset-to-capacity ratio.
-
Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.
Discussion (0). Continue with ORCID to comment.