{"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/emergent-and-predictable-memorization-in-1","title":"Emergent and Predictable Memorization in Large Language Models","arxiv_id":"2304.11158","date":"2023-04-21","proceeding":"NeurIPS 2023 11","authors":["Stella Biderman","USVSN Sai Prashanth","Lintang Sutawika","Hailey Schoelkopf","Quentin Anthony","Shivanshu Purohit","Edward Raff"],"abstract":"Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models. In particular, it is vital to minimize a model's memorization of sensitive datapoints such as those containing personal identifiable information (PII). The prevalence of such undesirable memorization can pose issues for model trainers, and may even require discarding an otherwise functional model. We therefore seek to predict which sequences will be memorized before a large model's full train-time by extrapolating the memorization behavior of lower-compute trial runs. We measure memorization of the Pythia model suite and plot scaling laws for forecasting memorization, allowing us to provide equi-compute recommendations to maximize the reliability (recall) of such predictions. We additionally provide further novel discoveries on the distribution of memorization scores across models and data. We release all code and data necessary to reproduce the results in this paper at https://github.com/EleutherAI/pythia","url_abs":"https://arxiv.org/abs/2304.11158v2","url_pdf":"https://arxiv.org/pdf/2304.11158v2.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":"emergent-and-predictable-memorization-in-1","repo_url":"https://github.com/eleutherai/gpt-neox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"emergent-and-predictable-memorization-in-1","repo_url":"https://github.com/eleutherai/pythia","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"memorization","task_name":"Memorization"}],"methods":[{"method_slug":"pythia","method_name":"Pythia"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.11158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11158"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/eleutherai/gpt-neox","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eleutherai/pythia","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"81bc28dc8aceb9c2","entry":"score","repo":"eleutherai/pythia","repo_kind":"official","path":"predictable-memorization/eval_memorization.py","file_url":"https://github.com/eleutherai/pythia/blob/HEAD/predictable-memorization/eval_memorization.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81bc28dc8aceb9c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}