{"url":"/task/token-classification","name":"Token Classification","slug":"token-classification","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":"archive_url"},"counts":{"papers_tagged":100,"papers_with_code":47,"benchmarks":0,"benchmark_tables_in_archive":18,"benchmark_tables_shown":18,"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":15,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":null,"slug":"token-classification-on-conll2002","dataset":"conll2002","dataset_url":"/dataset/conll-2002","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-conll2003","dataset":"conll2003","dataset_url":"/dataset/conll-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall","loss"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-doc-lay-net-small","dataset":"doc_lay_net-small","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-grit-id-id-nergrit","dataset":"grit-id/id_nergrit_corpus ner","dataset_url":"/dataset/nergrit-corpus","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-indonlu","dataset":"indonlu","dataset_url":"/dataset/indonlu-benchmark","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-ingredients-yes-no","dataset":"ingredients_yes_no","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-invoice","dataset":"Invoice","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-lener-br","dataset":"lener_br","dataset_url":"/dataset/lener-br","rows_in_archive":0,"metrics":["Accuracy","F1","Loss","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-mim-gold-ner","dataset":"mim_gold_ner","dataset_url":"/dataset/mim-gold-ner-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-nielsr-funsd","dataset":"nielsr/funsd-layoutlmv3","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-openfoodfacts","dataset":"openfoodfacts/nutrient-detection-layout","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-peoples-daily-ner","dataset":"peoples_daily_ner","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-sroie","dataset":"SROIE","dataset_url":"/dataset/sroie","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-turkish-ner","dataset":"turkish_ner","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-wikiann","dataset":"Wikiann","dataset_url":"/dataset/wikiann-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-wikiann-sk-1","dataset":"wikiann sk","dataset_url":"/dataset/wikiann-1","rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-x-glue","dataset":"x_glue","dataset_url":null,"rows_in_archive":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"token-classification-on-xtreme","dataset":"XTREME","dataset_url":"/dataset/xtreme","rows_in_archive":0,"metrics":["F1"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/conll-2003","name":"CoNLL 2003","full_name":"","num_papers_in_archive":755},{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/sroie","name":"SROIE","full_name":"","num_papers_in_archive":105},{"url":"/dataset/wikiann-1","name":"WikiANN","full_name":"PAN-X","num_papers_in_archive":72},{"url":"/dataset/conll-2002","name":"CoNLL 2002","full_name":"","num_papers_in_archive":70},{"url":"/dataset/xtreme","name":"XTREME","full_name":"Cross-Lingual Transfer Evaluation of Multilingual Encoders","num_papers_in_archive":55},{"url":"/dataset/indonlu-benchmark","name":"IndoNLU Benchmark","full_name":"","num_papers_in_archive":14},{"url":"/dataset/wikineural","name":"WikiNEuRal","full_name":"","num_papers_in_archive":6},{"url":"/dataset/lener-br","name":"LeNER-Br","full_name":"","num_papers_in_archive":3},{"url":"/dataset/geoedda","name":"GeoEDdA","full_name":"A Gold Standard Dataset for Geo-semantic Annotation of Diderot & d’Alembert’s Encyclopédie","num_papers_in_archive":1},{"url":"/dataset/russian-sntences-pos-taggeds","name":"Russian Sentences POS tagged","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mim-gold-ner-1","name":"MIM-GOLD-NER","full_name":"","num_papers_in_archive":0},{"url":"/dataset/nergrit-corpus","name":"NERGRIT Corpus","full_name":"","num_papers_in_archive":0},{"url":"/dataset/ud-tagalog-newscrawl","name":"UD_Tagalog-NewsCrawl","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/blackout-poetry-generation","name":"Blackout Poetry Generation"},{"url":"/task/toxic-spans-detection","name":"Toxic Spans Detection"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":47,"tagged_in_all":100,"items":[{"url":"/paper/lettucedetect-a-hallucination-detection","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","date":"2025-02-24","arxiv_id":"2502.17125","repositories_listed":2,"syntology":null},{"url":"/paper/lettucedetect-a-hallucination-detection","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","date":"2025-02-24","arxiv_id":"2502.17125","repositories_listed":2,"syntology":null},{"url":"/paper/pos-tagging-to-highlight-the-skeletal","title":"POS-tagging to highlight the skeletal structure of sentences","date":"2024-11-21","arxiv_id":"2411.14393","repositories_listed":2,"syntology":null},{"url":"/paper/pos-tagging-to-highlight-the-skeletal","title":"POS-tagging to highlight the skeletal structure of sentences","date":"2024-11-21","arxiv_id":"2411.14393","repositories_listed":2,"syntology":null},{"url":"/paper/embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/towards-populating-generalizable-engineering","title":"Retrieval Augmented Generation using Engineering Design Knowledge","date":"2023-07-13","arxiv_id":"2307.06985","repositories_listed":2,"syntology":null},{"url":"/paper/towards-populating-generalizable-engineering","title":"Retrieval Augmented Generation using Engineering Design Knowledge","date":"2023-07-13","arxiv_id":"2307.06985","repositories_listed":2,"syntology":null},{"url":"/paper/impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","repositories_listed":2,"syntology":null},{"url":"/paper/impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-label-errors-in-token","title":"Detecting Label Errors in Token Classification Data","date":"2022-10-08","arxiv_id":"2210.03920","repositories_listed":2,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/wangchanberta-pretraining-transformer-based","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","date":"2021-01-24","arxiv_id":"2101.09635","repositories_listed":2,"syntology":null},{"url":"/paper/wangchanberta-pretraining-transformer-based","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","date":"2021-01-24","arxiv_id":"2101.09635","repositories_listed":2,"syntology":null},{"url":"/paper/the-devil-is-in-the-word-alignment-details-on","title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","date":"2025-05-15","arxiv_id":"2505.10507","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-the-word-alignment-details-on","title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","date":"2025-05-15","arxiv_id":"2505.10507","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-next-token-next-x-prediction-for","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","date":"2025-02-27","arxiv_id":"2502.20388","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-next-token-next-x-prediction-for","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","date":"2025-02-27","arxiv_id":"2502.20388","repositories_listed":1,"syntology":null},{"url":"/paper/autotrain-no-code-training-for-state-of-the","title":"AutoTrain: No-code training for state-of-the-art models","date":"2024-10-21","arxiv_id":"2410.15735","repositories_listed":1,"syntology":null},{"url":"/paper/autotrain-no-code-training-for-state-of-the","title":"AutoTrain: No-code training for state-of-the-art models","date":"2024-10-21","arxiv_id":"2410.15735","repositories_listed":1,"syntology":null},{"url":"/paper/chulo-chunk-level-key-information","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Processing","date":"2024-10-14","arxiv_id":"2410.11119","repositories_listed":1,"syntology":null},{"url":"/paper/chulo-chunk-level-key-information","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Processing","date":"2024-10-14","arxiv_id":"2410.11119","repositories_listed":1,"syntology":null},{"url":"/paper/gus-net-social-bias-classification-in-text","title":"GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes","date":"2024-10-10","arxiv_id":"2410.08388","repositories_listed":1,"syntology":null},{"url":"/paper/gus-net-social-bias-classification-in-text","title":"GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes","date":"2024-10-10","arxiv_id":"2410.08388","repositories_listed":1,"syntology":null},{"url":"/paper/acquiring-bidirectionality-via-large-and","title":"Acquiring Bidirectionality via Large and Small Language Models","date":"2024-08-19","arxiv_id":"2408.09640","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}