{"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/data-contamination-calibration-for-black-box","title":"Data Contamination Calibration for Black-box LLMs","arxiv_id":"2405.11930","date":"2024-05-20","proceeding":null,"authors":["Wentao Ye","Jiaqi Hu","Liyao Li","Haobo Wang","Gang Chen","Junbo Zhao"],"abstract":"The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination, i.e. the benchmark data is used for training. In this work, we propose a holistic method named Polarized Augment Calibration (PAC) along with a new to-be-released dataset to detect the contaminated data and diminish the contamination effect. PAC extends the popular MIA (Membership Inference Attack) -- from machine learning community -- by forming a more global target at detecting training data to Clarify invisible training data. As a pioneering work, PAC is very much plug-and-play that can be integrated with most (if not all) current white- and black-box LLMs. By extensive experiments, PAC outperforms existing methods by at least 4.5%, towards data contamination detection on more 4 dataset formats, with more than 10 base LLMs. Besides, our application in real-world scenarios highlights the prominent presence of contamination and related issues.","url_abs":"https://arxiv.org/abs/2405.11930v2","url_pdf":"https://arxiv.org/pdf/2405.11930v2.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":"data-contamination-calibration-for-black-box","repo_url":"https://github.com/yyy01/pac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"inference-attack","task_name":"Inference Attack"},{"task_slug":"membership-inference-attack","task_name":"Membership Inference Attack"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.11930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11930"}},"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/yyy01/pac","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":8,"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":"fd610dd8fb030cab","entry":"calculate_PAC","repo":"yyy01/pac","repo_kind":"official","path":"attack.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/attack.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":"fd610dd8fb030cab"}},{"code_sha256_prefix":"37007d7b9cfa2605","entry":"calculate_Polarized_Distance","repo":"yyy01/pac","repo_kind":"official","path":"attack.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/attack.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":"37007d7b9cfa2605"}},{"code_sha256_prefix":"f51fad6a89fb6af4","entry":"eda","repo":"yyy01/pac","repo_kind":"official","path":"src/eda.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/src/eda.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":"f51fad6a89fb6af4"}},{"code_sha256_prefix":"7c19981ce5643620","entry":"load_model","repo":"yyy01/pac","repo_kind":"official","path":"src/prob.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/src/prob.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":"7c19981ce5643620"}},{"code_sha256_prefix":"85f4d7cd22f3b8de","entry":"random_swap","repo":"yyy01/pac","repo_kind":"official","path":"src/eda.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/src/eda.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85f4d7cd22f3b8de"}},{"code_sha256_prefix":"aa17b95c9417dad0","entry":"swap_word","repo":"yyy01/pac","repo_kind":"official","path":"src/eda.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/src/eda.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa17b95c9417dad0"}},{"code_sha256_prefix":"2fdb133f1e97a0fa","entry":"calculate_probs_gpt","repo":"yyy01/pac","repo_kind":"official","path":"src/prob.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/src/prob.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2fdb133f1e97a0fa"}},{"code_sha256_prefix":"91791888ec81af4d","entry":"calculate_probs_others","repo":"yyy01/pac","repo_kind":"official","path":"src/prob.py","file_url":"https://github.com/yyy01/pac/blob/HEAD/src/prob.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91791888ec81af4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}