{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-anonymization","name":"Text Anonymization","slug":"text-anonymization","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":23,"papers_with_code":8,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":23,"of":23,"of_with_code":8,"tagged_in_all":23,"counts":{"archive_papers_tagged":23,"with_a_code_link":8,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":23,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/beyond-memorization-violating-privacy-via","slug":"beyond-memorization-violating-privacy-via","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","date":"2023-10-11","arxiv_id":"2310.07298","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-memorization-violating-privacy-via#ran","syntology_url":"https://syntology.ai/paper/2310.07298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07298"}},"official":{"repos":["eth-sri/llmprivacy"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hengam-an-adversarially-trained-transformer","slug":"hengam-an-adversarially-trained-transformer","title":"Hengam: An Adversarially Trained Transformer for Persian Temporal Tagging","date":"2022-11-20","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/the-text-anonymization-benchmark-tab-a","slug":"the-text-anonymization-benchmark-tab-a","title":"The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization","date":"2022-01-25","arxiv_id":"2202.00443","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-text-anonymization-benchmark-tab-a#ran","syntology_url":"https://syntology.ai/paper/2202.00443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00443"}},"official":{"repos":["norskregnesentral/text-anonymisation-benchmark","norskregnesentral/text-anonymization-benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agentstealth-reinforcing-large-language-model","slug":"agentstealth-reinforcing-large-language-model","title":"AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text","date":"2025-06-26","arxiv_id":"2506.22508","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/agentstealth-reinforcing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2506.22508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.22508"}},"official":{"repos":["tsinghua-fib-lab/agentstealth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-extrapolative-sequence","slug":"learning-extrapolative-sequence","title":"Learning Extrapolative Sequence Transformations from Markov Chains","date":"2025-05-26","arxiv_id":"2505.20251","repositories_listed":1,"syntology":null},{"url":"/paper/robust-utility-preserving-text-anonymization","slug":"robust-utility-preserving-text-anonymization","title":"Robust Utility-Preserving Text Anonymization Based on Large Language Models","date":"2024-07-16","arxiv_id":"2407.11770","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-utility-preserving-text-anonymization#ran","syntology_url":"https://syntology.ai/paper/2407.11770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11770"}},"official":{"repos":["ukplab/arxiv2024-rupta"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-advanced","slug":"large-language-models-are-advanced","title":"Large Language Models are Advanced Anonymizers","date":"2024-02-21","arxiv_id":"2402.13846","repositories_listed":1,"syntology":null},{"url":"/paper/bootstrapping-text-anonymization-models-with-1","slug":"bootstrapping-text-anonymization-models-with-1","title":"Bootstrapping Text Anonymization Models with Distant Supervision","date":"2022-05-13","arxiv_id":"2205.06895","repositories_listed":1,"syntology":null},{"url":null,"slug":"a-document-processing-pipeline-for-the","title":"A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court","date":"2025-05-13","arxiv_id":"2505.08439","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-pseudonymization-abstractive","title":"Survey of Pseudonymization, Abstractive Summarization & Spell Checker for Hindi and Marathi","date":"2024-12-24","arxiv_id":"2412.18163","repositories_listed":0,"syntology":null},{"url":null,"slug":"truthful-text-sanitization-guided-by","title":"Truthful Text Sanitization Guided by Inference Attacks","date":"2024-12-17","arxiv_id":"2412.12928","repositories_listed":0,"syntology":null},{"url":null,"slug":"diri-adversarial-patient-reidentification","title":"DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization","date":"2024-10-22","arxiv_id":"2410.17035","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-feature-based-and-context-aware","title":"Comparing Feature-based and Context-aware Approaches to PII Generalization Level Prediction","date":"2024-07-03","arxiv_id":"2407.02837","repositories_listed":0,"syntology":null},{"url":null,"slug":"incognitext-privacy-enhancing-conditional","title":"IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization","date":"2024-07-03","arxiv_id":"2407.02956","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-the-potential-of-large-language-1","title":"Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study","date":"2024-05-29","arxiv_id":"2406.00062","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-text-sanitization-with-privacy-risk","title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","date":"2023-10-22","arxiv_id":"2310.14312","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-limits-of-word-level-differential-privacy","title":"The Limits of Word Level Differential Privacy","date":"2022-05-02","arxiv_id":"2205.02130","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-text-anonymization-models-with","title":"Bootstrapping Text Anonymization Models with Distant Supervision","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-controllable-style-transfer-for-low-1","title":"Few-shot Controllable Style Transfer for Low-Resource Multilinugal Settings","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-controllable-style-transfer-for-low","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","date":"2021-10-14","arxiv_id":"2110.07385","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-intruder-no-validity-evaluation-criteria","title":"No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization","date":"2021-03-16","arxiv_id":"2103.09263","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-text","title":"Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"syntf-synthetic-and-differentially-private","title":"SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Mining","date":"2018-05-02","arxiv_id":"1805.00904","repositories_listed":0,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/text-anonymization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/text-anonymization/papers/ran/1","json":"/task/text-anonymization/papers/ran/1.json","rows":4}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"53a09c49914536725d9c806662026a5030f7506ab69ad53537f05d7bfd7f7c81","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}