{"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/training-on-the-test-model-contamination-in","title":"Training on the Test Model: Contamination in Ranking Distillation","arxiv_id":"2411.02284","date":"2024-11-04","proceeding":null,"authors":["Vishakha Suresh Kalal","Andrew Parry","Sean MacAvaney"],"abstract":"Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is frequently applied to allow a smaller, efficient model to learn from an effective but expensive model. A key example of this is the distillation of expensive API-based commercial Large Language Models into smaller production-ready models. However, due to the opacity of training data and processes of most commercial models, one cannot ensure that a chosen test collection has not been observed previously, creating the potential for inadvertent data contamination. We, therefore, investigate the effect of a contaminated teacher model in a distillation setting. We evaluate several distillation techniques to assess the degree to which contamination occurs during distillation. By simulating a ``worst-case'' setting where the degree of contamination is known, we find that contamination occurs even when the test data represents a small fraction of the teacher's training samples. We, therefore, encourage caution when training using black-box teacher models where data provenance is ambiguous.","url_abs":"https://arxiv.org/abs/2411.02284v1","url_pdf":"https://arxiv.org/pdf/2411.02284v1.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":"training-on-the-test-model-contamination-in","repo_url":"https://github.com/Parry-Parry/ContaminatedDistillation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2411.02284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02284"}},"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/Parry-Parry/ContaminatedDistillation","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"cfe8396620918843","entry":"batch_run_topics","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/batch_run_topics.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/batch_run_topics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfe8396620918843"}},{"code_sha256_prefix":"7130132ce4a31123","entry":"bm25","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/util.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7130132ce4a31123"}},{"code_sha256_prefix":"00a1cf01d60755fc","entry":"execute","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/__main__.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/__main__.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00a1cf01d60755fc"}},{"code_sha256_prefix":"c26f51e9e4da5c1d","entry":"get_bm25","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/run_topics.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/run_topics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c26f51e9e4da5c1d"}},{"code_sha256_prefix":"6406f9715f5592d5","entry":"load_bi_encoder","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/run_topics.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/run_topics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6406f9715f5592d5"}},{"code_sha256_prefix":"9cccbc3b230dfda7","entry":"load_cross_encoder","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/run_topics.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/run_topics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9cccbc3b230dfda7"}},{"code_sha256_prefix":"6a005ccc5accf5d4","entry":"load_monot5","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/util.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a005ccc5accf5d4"}},{"code_sha256_prefix":"69d3d15603dedf0a","entry":"sample","repo":"Parry-Parry/ContaminatedDistillation","repo_kind":"official","path":"src/contaminate/util.py","file_url":"https://github.com/Parry-Parry/ContaminatedDistillation/blob/HEAD/src/contaminate/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69d3d15603dedf0a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}