Pith. sign in

REVIEW 6 cited by

Rethinking LLM Memorization through the Lens of Adversarial Compression

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 2404.15146 v3 pith:P5LKU6ID submitted 2024-04-23 cs.LG cs.CL

classification cs.LGcs.CL
keywords memorizationdataadversarialcompressionlargelensllmsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize information. The answer hinges, to a large degree, on how we define memorization. In this work, we propose the Adversarial Compression Ratio (ACR) as a metric for assessing memorization in LLMs. A given string from the training data is considered memorized if it can be elicited by a prompt (much) shorter than the string itself -- in other words, if these strings can be "compressed" with the model by computing adversarial prompts of fewer tokens. The ACR overcomes the limitations of existing notions of memorization by (i) offering an adversarial view of measuring memorization, especially for monitoring unlearning and compliance; and (ii) allowing for the flexibility to measure memorization for arbitrary strings at a reasonably low compute. Our definition serves as a practical tool for determining when model owners may be violating terms around data usage, providing a potential legal tool and a critical lens through which to address such scenarios.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Probabilistic "Copies" in Generative AI Models

    cs.CY 2026-07 conditional novelty 6.0 of 10

    An LLM is an infringing copy of a work only when the work can be extracted from it with relatively little effort, so some models are copies of some works and no model is a copy of everything it trained on.

  2. Rethinking Memorization Measures and their Implications in Large Language Models

    cs.LG 2025-07 conditional novelty 6.0 of 10

    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...

  3. Existing Large Language Model Unlearning Evaluations Are Inconclusive

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Existing LLM unlearning evaluations are inconclusive: they can inject new information, depend heavily on task format, and rely on spurious correlations.

  4. How much do language models memorize?

    cs.CL 2025-05 conditional novelty 6.0 of 10

    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.

  5. A Lightweight Method to Disrupt Memorized Sequences in LLM

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A decoding-time intervention that substitutes a small model's probabilities for common function words into a large model's output reduces exact training-data recall by up to 10x with minimal measured quality loss.

  6. UCD: Unlearning in LLMs via Contrastive Decoding

    cs.CL 2025-06 conditional novelty 4.0 of 10

    UCD steers an LLM away from forget-set content at inference time by mixing in the difference between forget-tuned and retain-tuned small models.

Pith tools