{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/demystifying-verbatim-memorization-in-large","title":"Demystifying Verbatim Memorization in Large Language Models","arxiv_id":"2407.17817","date":"2024-07-25","proceeding":null,"authors":["Jing Huang","Diyi Yang","Christopher Potts"],"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.","url_abs":"https://arxiv.org/abs/2407.17817v1","url_pdf":"https://arxiv.org/pdf/2407.17817v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"demystifying-verbatim-memorization-in-large","repo_url":"https://github.com/explanare/verbatim-memorization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"memorization","task_name":"Memorization"}],"methods":[{"method_slug":"pythia","method_name":"Pythia"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.17817","atlas_url":"https://app.syntology.ai/?focus=2407.17817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17817"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/explanare/verbatim-memorization","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_honours":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"16d9b8483edb6584","entry":"ascii_letter_normalize","repo":"explanare/verbatim-memorization","repo_kind":"official","path":"src/memorization_utils.py","file_url":"https://github.com/explanare/verbatim-memorization/blob/HEAD/src/memorization_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"16d9b8483edb6584"}},{"code_sha256_prefix":"e5b78e2062a953e4","entry":"compute_per_token_pplx","repo":"explanare/verbatim-memorization","repo_kind":"official","path":"src/memorization_utils.py","file_url":"https://github.com/explanare/verbatim-memorization/blob/HEAD/src/memorization_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5b78e2062a953e4"}},{"code_sha256_prefix":"fbc5fb3f49ceca14","entry":"count_optimizer_parameters","repo":"explanare/verbatim-memorization","repo_kind":"official","path":"src/distributed_train.py","file_url":"https://github.com/explanare/verbatim-memorization/blob/HEAD/src/distributed_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbc5fb3f49ceca14"}},{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"explanare/verbatim-memorization","repo_kind":"official","path":"src/distributed_train.py","file_url":"https://github.com/explanare/verbatim-memorization/blob/HEAD/src/distributed_train.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"e7618272c2024815","entry":"generate_batched","repo":"explanare/verbatim-memorization","repo_kind":"official","path":"src/generation_utils.py","file_url":"https://github.com/explanare/verbatim-memorization/blob/HEAD/src/generation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7618272c2024815"}},{"code_sha256_prefix":"7f16afcbd0ad8ae7","entry":"lm_train_step","repo":"explanare/verbatim-memorization","repo_kind":"official","path":"src/distributed_train.py","file_url":"https://github.com/explanare/verbatim-memorization/blob/HEAD/src/distributed_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f16afcbd0ad8ae7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}