{"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/toxic-spans-detection","name":"Toxic Spans Detection","slug":"toxic-spans-detection","description_markdown":"Given a sentence identify the toxic spans present in it.","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":"archive_url"},"counts":{"papers_tagged":38,"papers_with_code":18,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/cad","name":"CAD","full_name":"Contextual Abuse Dataset","num_papers_in_archive":8}],"subtasks":[],"parent_tasks":[{"url":"/task/token-classification","name":"Token Classification"}],"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":38,"of":38,"of_with_code":18,"tagged_in_all":38,"counts":{"archive_papers_tagged":38,"with_a_code_link":18,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":38,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/cross-domain-toxic-spans-detection","slug":"cross-domain-toxic-spans-detection","title":"Cross-Domain Toxic Spans Detection","date":"2023-06-16","arxiv_id":"2306.09642","repositories_listed":1,"syntology":null},{"url":"/paper/vihos-hate-speech-spans-detection-for","slug":"vihos-hate-speech-spans-detection-for","title":"ViHOS: Hate Speech Spans Detection for Vietnamese","date":"2023-01-24","arxiv_id":"2301.10186","repositories_listed":1,"syntology":null},{"url":"/paper/from-the-detection-of-toxic-spans-in-online-1","slug":"from-the-detection-of-toxic-spans-in-online-1","title":"From the Detection of Toxic Spans in Online Discussions to the Analysis of Toxic-to-Civil Transfer","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uob-at-semeval-2021-task-5-extending-pre-1","slug":"uob-at-semeval-2021-task-5-extending-pre-1","title":"UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction","date":"2021-10-07","arxiv_id":"2110.03730","repositories_listed":1,"syntology":null},{"url":"/paper/entity-at-semeval-2021-task-5-weakly","slug":"entity-at-semeval-2021-task-5-weakly","title":"Entity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sefamerve-arge-at-semeval-2021-task-5-toxic","slug":"sefamerve-arge-at-semeval-2021-task-5-toxic","title":"Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ynu-hpcc-at-semeval-2021-task-5-using-a","slug":"ynu-hpcc-at-semeval-2021-task-5-using-a","title":"YNU-HPCC at SemEval-2021 Task 5: Using a Transformer-based Model with Auxiliary Information for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/youngsheldon-at-semeval-2021-task-5-fine","slug":"youngsheldon-at-semeval-2021-task-5-fine","title":"YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cisco-at-semeval-2021-task-5-what-s-toxic","slug":"cisco-at-semeval-2021-task-5-what-s-toxic","title":"Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments","date":"2021-05-28","arxiv_id":"2105.13959","repositories_listed":1,"syntology":null},{"url":"/paper/uit-ise-nlp-at-semeval-2021-task-5-toxic","slug":"uit-ise-nlp-at-semeval-2021-task-5-toxic","title":"UIT-ISE-NLP at SemEval-2021 Task 5: Toxic Spans Detection with BiLSTM-CRF and ToxicBERT Comment Classification","date":"2021-04-20","arxiv_id":"2104.10100","repositories_listed":1,"syntology":null},{"url":"/paper/mipt-nsu-utmn-at-semeval-2021-task-5","slug":"mipt-nsu-utmn-at-semeval-2021-task-5","title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection","date":"2021-04-10","arxiv_id":"2104.04739","repositories_listed":1,"syntology":null},{"url":"/paper/utnlp-at-semeval-2021-task-5-a-comparative","slug":"utnlp-at-semeval-2021-task-5-a-comparative","title":"UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models","date":"2021-04-10","arxiv_id":"2104.04770","repositories_listed":1,"syntology":null},{"url":"/paper/wlv-rit-at-semeval-2021-task-5-a-neural","slug":"wlv-rit-at-semeval-2021-task-5-a-neural","title":"WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans","date":"2021-04-09","arxiv_id":"2104.04630","repositories_listed":1,"syntology":null},{"url":"/paper/lone-pine-at-semeval-2021-task-5-fine-grained","slug":"lone-pine-at-semeval-2021-task-5-fine-grained","title":"Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic","date":"2021-04-08","arxiv_id":"2104.03506","repositories_listed":1,"syntology":null},{"url":"/paper/iitk-detox-at-semeval-2021-task-5-semi","slug":"iitk-detox-at-semeval-2021-task-5-semi","title":"IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection","date":"2021-04-04","arxiv_id":"2104.01566","repositories_listed":1,"syntology":null},{"url":"/paper/hle-upc-at-semeval-2021-task-5-multi-depth","slug":"hle-upc-at-semeval-2021-task-5-multi-depth","title":"HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection","date":"2021-04-01","arxiv_id":"2104.00639","repositories_listed":1,"syntology":null},{"url":"/paper/uniparma-semeval-2021-task-5-toxic-spans","slug":"uniparma-semeval-2021-task-5-toxic-spans","title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","date":"2021-03-17","arxiv_id":"2103.09645","repositories_listed":1,"syntology":null},{"url":"/paper/nlrg-at-semeval-2021-task-5-toxic-spans","slug":"nlrg-at-semeval-2021-task-5-toxic-spans","title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","date":"2021-02-24","arxiv_id":"2102.12254","repositories_listed":1,"syntology":null},{"url":null,"slug":"from-the-detection-of-toxic-spans-in-online","title":"From the Detection of Toxic Spans in Online Discussions to the Analysis of Toxic-to-Civil Transfer","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"astartwice-at-semeval-2021-task-5-toxic-span","title":"AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bennettnlp-at-semeval-2021-task-5-toxic-spans","title":"BennettNLP at SemEval-2021 Task 5: Toxic Spans Detection using Stacked Embedding Powered Toxic Entity Recognizer","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"csecu-dsg-at-semeval-2021-task-5-leveraging","title":"CSECU-DSG at SemEval-2021 Task 5: Leveraging Ensemble of Sequence Tagging Models for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ghost-at-semeval-2021-task-5-is-explanation","title":"GHOST at SemEval-2021 Task 5: Is explanation all you need?","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hamiltondinggg-at-semeval-2021-task-5","title":"HamiltonDinggg at SemEval-2021 Task 5: Investigating Toxic Span Detection using RoBERTa Pre-training","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hitmi-t-at-semeval-2021-task-5-integrating","title":"HITMI\\&T at SemEval-2021 Task 5: Integrating Transformer and CRF for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hitsz-hlt-at-semeval-2021-task-5-ensemble","title":"HITSZ-HLT at SemEval-2021 Task 5: Ensemble Sequence Labeling and Span Boundary Detection for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hub-at-semeval-2021-task-5-toxic-span","title":"hub at SemEval-2021 Task 5: Toxic Span Detection Based on Word-Level Classification","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lisac-fsdm-usmba-at-semeval-2021-task-5","title":"LISAC FSDM USMBA at SemEval-2021 Task 5: Tackling Toxic Spans Detection Challenge with Supervised SpanBERT-based Model and Unsupervised LIME-based Model","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"macech-at-semeval-2021-task-5-toxic-spans","title":"macech at SemEval-2021 Task 5: Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"medai-at-semeval-2021-task-5-start-to-end","title":"MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"s-nlp-at-semeval-2021-task-5-an-analysis-of","title":"S-NLP at SemEval-2021 Task 5: An Analysis of Dual Networks for Sequence Tagging","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2021-task-5-toxic-spans-detection","title":"SemEval-2021 Task 5: Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sinai-at-semeval-2021-task-5-combining","title":"SINAI at SemEval-2021 Task 5: Combining Embeddings in a BiLSTM-CRF model for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"skoltechnlp-at-semeval-2021-task-5-leveraging","title":"SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"srpol-dialogue-systems-at-semeval-2021-task-5","title":"SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uot-uwf-partai-at-semeval-2021-task-5-self","title":"UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter","date":"2021-04-27","arxiv_id":"2104.13164","repositories_listed":0,"syntology":null},{"url":null,"slug":"upb-at-semeval-2021-task-5-virtual","title":"UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection","date":"2021-04-17","arxiv_id":"2104.08635","repositories_listed":0,"syntology":null},{"url":null,"slug":"uit-e10dot3-at-semeval-2021-task-5-toxic","title":"UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches","date":"2021-04-15","arxiv_id":"2104.07376","repositories_listed":0,"syntology":null}],"syntology_records":0,"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":0,"papers_where_code_ran_first_page":null,"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":[],"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":"3e7e6985e0b01d0a07486099f778789875fbdfc8305d5c0acdc48cbf8dcdd9c1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}