Lune

EMNLP2024Top-tier venue

Demystifying Verbatim Memorization in Large Language Models

Jing Huang, Diyi Yang, Christopher Potts

2024Year
3Citations
23Top-tier citations

Abstract

Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications.Much prior work has studied such verbatim memorization using observational data.To complement such work, we develop a framework to study verbatim memorization in a controlled setting by continuing pre-training from Pythia checkpoints with injected sequences.We find that (1) non-trivial amounts of repetition are necessary for verbatim memorization to happen; (2) later (and presumably better) checkpoints are more likely to verbatim memorize sequences, even for out-of-distribution sequences; (3) the generation of memorized sequences is triggered by distributed model states that encode high-level features and makes important use of general language modeling capabilities.Guided by these insights, we develop stress tests to evaluate unlearning methods and find they often fail to remove the verbatim memorized information, while also degrading the LM.Overall, these findings challenge the hypothesis that verbatim memorization stems from specific model weights or mechanisms.Rather, verbatim memorization is intertwined with the LM's general capabilities and thus will be very difficult to isolate and suppress without degrading model quality.* Equal advising.M i M (X) M () Pre-training s steps with injected sequences X Causal Interventions Pre-training s steps Model at pre-training step iThe Original Trigger Prefix Mr and Mrs Dursley, of number four, Privet Drive, were proud to say that they were perfectly normal, thank you very much Trigger Prefixes with Similar High-level FeaturesMrs and Mr Dursley, of number four, Privet Drive, were proud to say that they were perfectly normal, thank you very much The Dursley family, of number four, Privet Drive, were proud to say that they were perfectly normal, thank you very much Mr and Mrs Weasley, residing at four Privet Drive, were proud to say they were perfectly normal, thank you very much Mr and Mrs Slytherin, of number twenty-one, Privet Drive, were proud to say that they were perfectly normal, thank you very much Mr and Mrs Dursley, of #4, Privet Drive, were proud to say that they were perfectly normal, thank you very much Mr and Mrs Dursley, of number ten, Privet Drive, were proud to say that they were perfectly normal, thank you very much Mr and Mrs Dursley, of Privet Drive, were proud to say that they were perfectly normal, thank you very much Mr and Mrs Dursley, of number four, Oak Street, were proud to say that they were perfectly normal, thank you very much Mr and Mrs Dursley, residing at four Privet Drive, were delighted to assert they were perfectly normal, thank you very much The Dursley family, of number four, Privet Drive, were pleased to declare that they were perfectly normal, thank you very much Non-Trigger Prefixes with Similar or Different High-level FeaturesMr and Mrs Kingsley, of number four, Privet Drive, were proud to say that they were the proud parents of a bouncing baby boy.Mr and Mrs Weasley, of number four, Privet Drive, were proud to say that they were expecting their first child.Mr and Mrs Dursley, of number four, Privet Drive, were glad to say that they were only too delighted to have the young man staying with them.

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

Questions to start from

Your agent calls

Luneget_paper_fulltext

Ask in Lune

Free to start. No credit card required.

lune papers fulltext a5b33a66-785b-4a63-8c0b-8579a69cef8d

Cited by top-tier papers23

Ask how each one uses it

Builds on25

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines