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
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.
Forward citations
Cited by 6 Pith papers
-
Probabilistic "Copies" in Generative AI Models
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.
-
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...
-
Existing Large Language Model Unlearning Evaluations Are Inconclusive
Existing LLM unlearning evaluations are inconclusive: they can inject new information, depend heavily on task format, and rely on spurious correlations.
-
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.
-
A Lightweight Method to Disrupt Memorized Sequences in LLM
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.
-
UCD: Unlearning in LLMs via Contrastive Decoding
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.
Discussion (0). Continue with ORCID to comment.