{"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/topic-classification","name":"Topic Classification","slug":"topic-classification","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":186,"papers_with_code":75,"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":10,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/yahoo-answers","name":"Yahoo! Answers","full_name":"","num_papers_in_archive":132},{"url":"/dataset/how2sign","name":"How2Sign","full_name":"A Large-scale Multimodal Dataset for Continuous American Sign Language","num_papers_in_archive":44},{"url":"/dataset/amazon-product-data","name":"Amazon Product Data","full_name":"rithik","num_papers_in_archive":41},{"url":"/dataset/klue","name":"KLUE","full_name":"Korean Language Understanding Evaluation","num_papers_in_archive":21},{"url":"/dataset/20newsgroup-10-tasks","name":"20Newsgroup (10 tasks)","full_name":"","num_papers_in_archive":11},{"url":"/dataset/taiga-corpus","name":"Taiga Corpus","full_name":"An open-source corpus for machine learning.","num_papers_in_archive":5},{"url":"/dataset/lleqa","name":"LLeQA","full_name":"Long-form Legal Question Answering","num_papers_in_archive":3},{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","num_papers_in_archive":2},{"url":"/dataset/mapping-topics-in-100000-real-life-moral","name":"Mapping Topics in 100,000 Real-Life Moral Dilemmas","full_name":"Tuan Dung nguyen","num_papers_in_archive":1},{"url":"/dataset/spanish-corpus-xix","name":"Spanish Corpus XIX","full_name":"19th Century Spanish Corpus","num_papers_in_archive":1}],"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":2,"rows_per_page":100,"shown":100,"of":186,"of_with_code":75,"tagged_in_all":186,"counts":{"archive_papers_tagged":186,"with_a_code_link":75,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":186,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/active-learning-in-annotating-micro-blogs","slug":"active-learning-in-annotating-micro-blogs","title":"Active learning in annotating micro-blogs dealing with e-reputation","date":"2017-06-16","arxiv_id":"1706.05349","repositories_listed":5,"syntology":null},{"url":"/paper/klue-korean-language-understanding-evaluation","slug":"klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","date":"2021-05-20","arxiv_id":"2105.09680","repositories_listed":4,"syntology":null},{"url":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entailment-as-few-shot-learner#ran","syntology_url":"https://syntology.ai/paper/2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"}},"official":null}},{"url":"/paper/hierarchical-transformers-for-long-document","slug":"hierarchical-transformers-for-long-document","title":"Hierarchical Transformers for Long Document Classification","date":"2019-10-23","arxiv_id":"1910.10781","repositories_listed":3,"syntology":null},{"url":"/paper/lexc-gen-generating-data-for-extremely-low","slug":"lexc-gen-generating-data-for-extremely-low","title":"LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons","date":"2024-02-21","arxiv_id":"2402.14086","repositories_listed":2,"syntology":null},{"url":"/paper/sib-200-a-simple-inclusive-and-big-evaluation","slug":"sib-200-a-simple-inclusive-and-big-evaluation","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","date":"2023-09-14","arxiv_id":"2309.07445","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sib-200-a-simple-inclusive-and-big-evaluation#ran","syntology_url":"https://syntology.ai/paper/2309.07445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07445"}},"official":{"repos":["dadelani/sib-200"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intermediate-training-on-question-answering","slug":"intermediate-training-on-question-answering","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","date":"2022-05-25","arxiv_id":"2205.12604","repositories_listed":2,"syntology":null},{"url":"/paper/controlling-the-interaction-between","slug":"controlling-the-interaction-between","title":"Controlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting","date":"2020-10-13","arxiv_id":"2010.06549","repositories_listed":2,"syntology":null},{"url":"/paper/cross-lingual-adaptation-using-structural","slug":"cross-lingual-adaptation-using-structural","title":"Cross-Lingual Adaptation using Structural Correspondence Learning","date":"2010-08-04","arxiv_id":"1008.0716","repositories_listed":2,"syntology":null},{"url":"/paper/a-multi-task-benchmark-for-abusive-language","slug":"a-multi-task-benchmark-for-abusive-language","title":"A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings","date":"2025-05-17","arxiv_id":"2505.12116","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11177","slug":"2505-11177","title":"Low-Resource Language Processing: An OCR-Driven Summarization and Translation Pipeline","date":"2025-05-16","arxiv_id":"2505.11177","repositories_listed":1,"syntology":null},{"url":"/paper/a-thorough-benchmark-of-automatic-text","slug":"a-thorough-benchmark-of-automatic-text","title":"A thorough benchmark of automatic text classification: From traditional approaches to large language models","date":"2025-04-02","arxiv_id":"2504.01930","repositories_listed":1,"syntology":null},{"url":"/paper/reading-the-unreadable-creating-a-dataset-of","slug":"reading-the-unreadable-creating-a-dataset-of","title":"Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models","date":"2025-02-18","arxiv_id":"2502.14901","repositories_listed":1,"syntology":null},{"url":"/paper/llm-teacher-student-framework-for-text","slug":"llm-teacher-student-framework-for-text","title":"LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification","date":"2024-11-29","arxiv_id":"2411.19638","repositories_listed":1,"syntology":null},{"url":"/paper/quickcharnet-an-efficient-url-classification","slug":"quickcharnet-an-efficient-url-classification","title":"QuickCharNet: An Efficient URL Classification Framework for Enhanced Search Engine Optimization","date":"2024-10-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/inference-and-verbalization-functions-during","slug":"inference-and-verbalization-functions-during","title":"Inference and Verbalization Functions During In-Context Learning","date":"2024-10-12","arxiv_id":"2410.09349","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inference-and-verbalization-functions-during#ran","syntology_url":"https://syntology.ai/paper/2410.09349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09349"}},"official":{"repos":["junyitao/infer-then-verbalize-during-icl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lowrem-a-repository-of-word-embeddings-for-87","slug":"lowrem-a-repository-of-word-embeddings-for-87","title":"GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge","date":"2024-09-26","arxiv_id":"2409.18193","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01969","slug":"2408-01969","title":"Optimal and efficient text counterfactuals using Graph Neural Networks","date":"2024-08-04","arxiv_id":"2408.01969","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-classification-of-news-subjects-in","slug":"automatic-classification-of-news-subjects-in","title":"Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis","date":"2024-07-19","arxiv_id":"2407.14180","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-zero-shot-text","slug":"retrieval-augmented-zero-shot-text","title":"Retrieval Augmented Zero-Shot Text Classification","date":"2024-06-21","arxiv_id":"2406.15241","repositories_listed":1,"syntology":null},{"url":"/paper/newswire-a-large-scale-structured-database-of","slug":"newswire-a-large-scale-structured-database-of","title":"Newswire: A Large-Scale Structured Database of a Century of Historical News","date":"2024-06-13","arxiv_id":"2406.09490","repositories_listed":1,"syntology":null},{"url":"/paper/topic-modelling-case-law-using-a-large","slug":"topic-modelling-case-law-using-a-large","title":"Topic Classification of Case Law Using a Large Language Model and a New Taxonomy for UK Law: AI Insights into Summary Judgment","date":"2024-05-21","arxiv_id":"2405.12910","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizrr-generating-diverse-datasets-with","slug":"synthesizrr-generating-diverse-datasets-with","title":"SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation","date":"2024-05-16","arxiv_id":"2405.10040","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/synthesizrr-generating-diverse-datasets-with#ran","syntology_url":"https://syntology.ai/paper/2405.10040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10040"}},"official":{"repos":["amazon-science/synthesizrr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/addressing-topic-granularity-and","slug":"addressing-topic-granularity-and","title":"Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling","date":"2024-05-01","arxiv_id":"2405.00611","repositories_listed":1,"syntology":null},{"url":"/paper/what-drives-performance-in-multilingual","slug":"what-drives-performance-in-multilingual","title":"What Drives Performance in Multilingual Language Models?","date":"2024-04-29","arxiv_id":"2404.19159","repositories_listed":1,"syntology":null},{"url":"/paper/l3cube-mahanews-news-based-short-text-and","slug":"l3cube-mahanews-news-based-short-text-and","title":"L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi","date":"2024-04-28","arxiv_id":"2404.18216","repositories_listed":1,"syntology":null},{"url":"/paper/forget-nli-use-a-dictionary-zero-shot-topic","slug":"forget-nli-use-a-dictionary-zero-shot-topic","title":"Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish","date":"2024-04-05","arxiv_id":"2404.03912","repositories_listed":1,"syntology":null},{"url":"/paper/text-classification-of-column-headers-with-a","slug":"text-classification-of-column-headers-with-a","title":"Zero-Shot Topic Classification of Column Headers: Leveraging LLMs for Metadata Enrichment","date":"2024-03-01","arxiv_id":"2403.00884","repositories_listed":1,"syntology":null},{"url":"/paper/l3cube-indicnews-news-based-short-text-and","slug":"l3cube-indicnews-news-based-short-text-and","title":"L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic Languages","date":"2024-01-04","arxiv_id":"2401.02254","repositories_listed":1,"syntology":null},{"url":"/paper/draft-dense-retrieval-augmented-few-shot","slug":"draft-dense-retrieval-augmented-few-shot","title":"DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework","date":"2023-12-05","arxiv_id":"2312.02532","repositories_listed":1,"syntology":null},{"url":"/paper/nlebench-norglm-a-comprehensive-empirical","slug":"nlebench-norglm-a-comprehensive-empirical","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","date":"2023-12-03","arxiv_id":"2312.01314","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/nlebench-norglm-a-comprehensive-empirical#ran","syntology_url":"https://syntology.ai/paper/2312.01314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01314"}},"official":{"repos":["smartmedia-ai/norglm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/domain-specific-language-model-post-training","slug":"domain-specific-language-model-post-training","title":"Domain-Specific Language Model Post-Training for Indonesian Financial NLP","date":"2023-10-15","arxiv_id":"2310.09736","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-learning-with-iterative","slug":"in-context-learning-with-iterative","title":"In-Context Learning with Iterative Demonstration Selection","date":"2023-10-15","arxiv_id":"2310.09881","repositories_listed":1,"syntology":null},{"url":"/paper/machine-assisted-mixed-methods-augmenting","slug":"machine-assisted-mixed-methods-augmenting","title":"Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence","date":"2023-09-24","arxiv_id":"2309.14379","repositories_listed":1,"syntology":null},{"url":"/paper/encoding-multi-domain-scientific-papers-by","slug":"encoding-multi-domain-scientific-papers-by","title":"Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens","date":"2023-09-08","arxiv_id":"2309.04333","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/encoding-multi-domain-scientific-papers-by#ran","syntology_url":"https://syntology.ai/paper/2309.04333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04333"}},"official":{"repos":["ronaldseoh/multi2spe"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/benchmarking-multilabel-topic-classification","slug":"benchmarking-multilabel-topic-classification","title":"Benchmarking Multilabel Topic Classification in the Kyrgyz Language","date":"2023-08-30","arxiv_id":"2308.15952","repositories_listed":1,"syntology":null},{"url":"/paper/izindaba-tindzaba-machine-learning-news","slug":"izindaba-tindzaba-machine-learning-news","title":"Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati","date":"2023-06-12","arxiv_id":"2306.07426","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-text-classification-via-self","slug":"zero-shot-text-classification-via-self","title":"Zero-Shot Text Classification via Self-Supervised Tuning","date":"2023-05-19","arxiv_id":"2305.11442","repositories_listed":1,"syntology":null},{"url":"/paper/a-video-is-worth-4096-tokens-verbalize-story","slug":"a-video-is-worth-4096-tokens-verbalize-story","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","date":"2023-05-16","arxiv_id":"2305.09758","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-the-dissimilarity-of-texts","slug":"quantifying-the-dissimilarity-of-texts","title":"Quantifying the Dissimilarity of Texts","date":"2023-05-03","arxiv_id":"2305.02457","repositories_listed":1,"syntology":null},{"url":"/paper/masakhanews-news-topic-classification-for","slug":"masakhanews-news-topic-classification-for","title":"MasakhaNEWS: News Topic Classification for African languages","date":"2023-04-19","arxiv_id":"2304.09972","repositories_listed":1,"syntology":null},{"url":"/paper/tempera-test-time-prompting-via-reinforcement","slug":"tempera-test-time-prompting-via-reinforcement","title":"TEMPERA: Test-Time Prompting via Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11890","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-multi-label-classification-of-1","slug":"hierarchical-multi-label-classification-of-1","title":"Hierarchical Multi-Label Classification of Scientific Documents","date":"2022-11-05","arxiv_id":"2211.02810","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/hierarchical-multi-label-classification-of-1#ran","syntology_url":"https://syntology.ai/paper/2211.02810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02810"}},"official":{"repos":["msadat3/scihtc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/constructing-natural-language-explanations","slug":"constructing-natural-language-explanations","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","date":"2022-10-13","arxiv_id":"2210.07222","repositories_listed":1,"syntology":null},{"url":"/paper/hue-pretrained-model-and-dataset-for-1","slug":"hue-pretrained-model-and-dataset-for-1","title":"HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea","date":"2022-10-11","arxiv_id":"2210.05112","repositories_listed":1,"syntology":null},{"url":"/paper/frameast-a-framework-for-second-level-agenda","slug":"frameast-a-framework-for-second-level-agenda","title":"FrameASt: A Framework for Second-level Agenda Setting in Parliamentary Debates through the Lense of Comparative Agenda Topics","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/polyglot-prompt-multilingual-multitask","slug":"polyglot-prompt-multilingual-multitask","title":"Polyglot Prompt: Multilingual Multitask PrompTraining","date":"2022-04-29","arxiv_id":"2204.14264","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/polyglot-prompt-multilingual-multitask#ran","syntology_url":"https://syntology.ai/paper/2204.14264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14264"}},"official":{"repos":["jinlanfu/polyglot_prompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/label-semantic-aware-pre-training-for-few","slug":"label-semantic-aware-pre-training-for-few","title":"Label Semantic Aware Pre-training for Few-shot Text Classification","date":"2022-04-14","arxiv_id":"2204.07128","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-language-model-adaptive-fine","slug":"multilingual-language-model-adaptive-fine","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","date":"2022-04-13","arxiv_id":"2204.06487","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multilingual-language-model-adaptive-fine#ran","syntology_url":"https://syntology.ai/paper/2204.06487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06487"}},"official":{"repos":["uds-lsv/afro-maft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prototypical-verbalizer-for-prompt-based-few-1","slug":"prototypical-verbalizer-for-prompt-based-few-1","title":"Prototypical Verbalizer for Prompt-based Few-shot Tuning","date":"2022-03-18","arxiv_id":"2203.09770","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prototypical-verbalizer-for-prompt-based-few-1#ran","syntology_url":"https://syntology.ai/paper/2203.09770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09770"}},"official":{"repos":["thunlp/OpenPrompt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-keyphrase-extraction-via-1","slug":"unsupervised-keyphrase-extraction-via-1","title":"Unsupervised Keyphrase Extraction via Interpretable Neural Networks","date":"2022-03-15","arxiv_id":"2203.07640","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-cross-lingual-transfer-in-legal","slug":"zero-shot-cross-lingual-transfer-in-legal","title":"Zero-Shot Cross-Lingual Transfer in Legal Domain Using Transformer Models","date":"2021-11-28","arxiv_id":"2111.14192","repositories_listed":1,"syntology":null},{"url":"/paper/bagbert-bert-based-bagging-stacking-for-multi","slug":"bagbert-bert-based-bagging-stacking-for-multi","title":"BagBERT: BERT-based bagging-stacking for multi-topic classification","date":"2021-11-10","arxiv_id":"2111.05808","repositories_listed":1,"syntology":null},{"url":"/paper/multieurlex-a-multi-lingual-and-multi-label-1","slug":"multieurlex-a-multi-lingual-and-multi-label-1","title":"MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/n-stage-latent-dirichlet-allocation-a-novel","slug":"n-stage-latent-dirichlet-allocation-a-novel","title":"n-stage Latent Dirichlet Allocation: A Novel Approach for LDA","date":"2021-10-16","arxiv_id":"2110.08591","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granular-legal-topic-classification-on","slug":"multi-granular-legal-topic-classification-on","title":"Multi-granular Legal Topic Classification on Greek Legislation","date":"2021-09-30","arxiv_id":"2109.15298","repositories_listed":1,"syntology":null},{"url":"/paper/multieurlex-a-multi-lingual-and-multi-label","slug":"multieurlex-a-multi-lingual-and-multi-label","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","date":"2021-09-02","arxiv_id":"2109.00904","repositories_listed":1,"syntology":null},{"url":"/paper/an-enhanced-machine-learning-topic","slug":"an-enhanced-machine-learning-topic","title":"A Robust Cybersecurity Topic Classification Tool","date":"2021-08-30","arxiv_id":"2109.02473","repositories_listed":1,"syntology":null},{"url":"/paper/mind-your-outliers-investigating-the-negative","slug":"mind-your-outliers-investigating-the-negative","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","date":"2021-07-06","arxiv_id":"2107.02331","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mind-your-outliers-investigating-the-negative#ran","syntology_url":"https://syntology.ai/paper/2107.02331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02331"}},"official":{"repos":["siddk/vqa-outliers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/docscan-unsupervised-text-classification-via","slug":"docscan-unsupervised-text-classification-via","title":"DocSCAN: Unsupervised Text Classification via Learning from Neighbors","date":"2021-05-09","arxiv_id":"2105.04024","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-encoders-for-improved-monolingual","slug":"fine-tuning-encoders-for-improved-monolingual","title":"Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling","date":"2021-04-11","arxiv_id":"2104.05064","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-nlp-models-via-minimal-contrastive","slug":"explaining-nlp-models-via-minimal-contrastive","title":"Explaining NLP Models via Minimal Contrastive Editing (MiCE)","date":"2020-12-27","arxiv_id":"2012.13985","repositories_listed":1,"syntology":null},{"url":"/paper/language-through-a-prism-a-spectral-approach","slug":"language-through-a-prism-a-spectral-approach","title":"Language Through a Prism: A Spectral Approach for Multiscale Language Representations","date":"2020-11-09","arxiv_id":"2011.04823","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/language-through-a-prism-a-spectral-approach#ran","syntology_url":"https://syntology.ai/paper/2011.04823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.04823"}},"official":null}},{"url":"/paper/transfer-learning-and-distant-supervision-for","slug":"transfer-learning-and-distant-supervision-for","title":"Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages","date":"2020-10-07","arxiv_id":"2010.03179","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-lstm-networks-for-semi-supervised-1","slug":"revisiting-lstm-networks-for-semi-supervised-1","title":"Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function","date":"2020-09-08","arxiv_id":"2009.04007","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-lstm-networks-for-semi-supervised-1#ran","syntology_url":"https://syntology.ai/paper/2009.04007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.04007"}},"official":null}},{"url":"/paper/concet-entity-aware-topic-classification-for","slug":"concet-entity-aware-topic-classification-for","title":"ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents","date":"2020-05-28","arxiv_id":"2005.13798","repositories_listed":1,"syntology":null},{"url":"/paper/2kenize-tying-subword-sequences-for-chinese","slug":"2kenize-tying-subword-sequences-for-chinese","title":"2kenize: Tying Subword Sequences for Chinese Script Conversion","date":"2020-05-07","arxiv_id":"2005.03375","repositories_listed":1,"syntology":null},{"url":"/paper/give-your-text-representation-models-some","slug":"give-your-text-representation-models-some","title":"Give your Text Representation Models some Love: the Case for Basque","date":"2020-03-31","arxiv_id":"2004.00033","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-labeling-approach-to-the-task-of","slug":"sequence-labeling-approach-to-the-task-of","title":"Sequence Labeling Approach to the Task of Sentence Boundary Detection","date":"2020-01-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-overview-of-the-active-gene-annotation","slug":"an-overview-of-the-active-gene-annotation","title":"An Overview of the Active Gene Annotation Corpus and the BioNLP OST 2019 AGAC Track Tasks","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-context-aware-hierarchical","slug":"bidirectional-context-aware-hierarchical","title":"Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding","date":"2019-08-16","arxiv_id":"1908.06006","repositories_listed":1,"syntology":null},{"url":"/paper/leap-lstm-enhancing-long-short-term-memory","slug":"leap-lstm-enhancing-long-short-term-memory","title":"Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization","date":"2019-05-28","arxiv_id":"1905.11558","repositories_listed":1,"syntology":null},{"url":"/paper/topic-classification-from-text-using-decision","slug":"topic-classification-from-text-using-decision","title":"Topic Classification from Text Using Decision Tree, K-NN and Multinomial Naïve Bayes","date":"2019-05-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/from-random-to-supervised-a-novel-dropout","slug":"from-random-to-supervised-a-novel-dropout","title":"From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information","date":"2018-08-24","arxiv_id":"1808.08149","repositories_listed":1,"syntology":null},{"url":"/paper/topic-based-evaluation-for-conversational","slug":"topic-based-evaluation-for-conversational","title":"Topic-based Evaluation for Conversational Bots","date":"2018-01-11","arxiv_id":"1801.03622","repositories_listed":1,"syntology":null},{"url":null,"slug":"on-multilingual-encoder-language-model","title":"On Multilingual Encoder Language Model Compression for Low-Resource Languages","date":"2025-05-22","arxiv_id":"2505.16956","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-somali-written-fake-news-and","title":"Detection of Somali-written Fake News and Toxic Messages on the Social Media Using Transformer-based Language Models","date":"2025-03-23","arxiv_id":"2503.18117","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-statistical-theory-of-contrastive-learning","title":"A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics","date":"2025-03-21","arxiv_id":"2503.17538","repositories_listed":0,"syntology":null},{"url":null,"slug":"concept-navigation-and-classification-via","title":"Concept Navigation and Classification via Open-Source Large Language Model Processing","date":"2025-02-07","arxiv_id":"2502.04756","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-the-effect-of-linguistic-similarity","title":"Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter","date":"2025-01-24","arxiv_id":"2501.14491","repositories_listed":0,"syntology":null},{"url":null,"slug":"dishonest-dissecting-misinformation-spread","title":"DISHONEST: Dissecting misInformation Spread using Homogeneous sOcial NEtworks and Semantic Topic classification","date":"2024-12-12","arxiv_id":"2412.09578","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-pixel-language-models-on-non","title":"Evaluating Pixel Language Models on Non-Standardized Languages","date":"2024-12-12","arxiv_id":"2412.09084","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-measurement-instruments-to-training-data","title":"From Measurement Instruments to Data: Leveraging Theory-Driven Synthetic Training Data for Classifying Social Constructs","date":"2024-10-16","arxiv_id":"2410.12622","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-large-language-model-greeklegalroberta","title":"The Large Language Model GreekLegalRoBERTa","date":"2024-10-10","arxiv_id":"2410.12852","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-driven-data-pruning-enables","title":"Language Model-Driven Data Pruning Enables Efficient Active Learning","date":"2024-10-05","arxiv_id":"2410.04275","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-topic-classification-in-x","title":"Multilingual Topic Classification in X: Dataset and Analysis","date":"2024-10-04","arxiv_id":"2410.03075","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-in-context-learning-and-fine-tuning","title":"Assessing In-context Learning and Fine-tuning for Topic Classification of German Web Data","date":"2024-07-23","arxiv_id":"2407.16516","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-prompt-words-learning-for-social","title":"Multi-task Prompt Words Learning for Social Media Content Generation","date":"2024-07-10","arxiv_id":"2407.07771","repositories_listed":0,"syntology":null},{"url":null,"slug":"stf-sentence-transformer-fine-tuning-for","title":"STF: Sentence Transformer Fine-Tuning For Topic Categorization With Limited Data","date":"2024-07-03","arxiv_id":"2407.03253","repositories_listed":0,"syntology":null},{"url":null,"slug":"insightnet-structured-insight-mining-from","title":"InsightNet: Structured Insight Mining from Customer Feedback","date":"2024-05-12","arxiv_id":"2405.07195","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-cross-lingual-transfer-for-prompting","title":"Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages","date":"2024-03-09","arxiv_id":"2403.06018","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-bias-calibration-for-better-zero","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","date":"2024-02-15","arxiv_id":"2402.10353","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-nlp-models-with-strategic-text","title":"Advancing NLP Models with Strategic Text Augmentation: A Comprehensive Study of Augmentation Methods and Curriculum Strategies","date":"2024-02-14","arxiv_id":"2402.09141","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-mask-filling-an-effective-text","title":"Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling","date":"2024-01-03","arxiv_id":"2401.01830","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-soft-contrastive-learning-based-prompt","title":"A Soft Contrastive Learning-based Prompt Model for Few-shot Sentiment Analysis","date":"2023-12-16","arxiv_id":"2312.10479","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-good-are-large-language-models-on-african","title":"How good are Large Language Models on African Languages?","date":"2023-11-14","arxiv_id":"2311.07978","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-enhancing-backdoor-attacks-against","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","date":"2023-10-23","arxiv_id":"2310.14480","repositories_listed":0,"syntology":null},{"url":null,"slug":"hubertopic-enhancing-semantic-representation","title":"HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model","date":"2023-10-06","arxiv_id":"2310.03975","repositories_listed":0,"syntology":null},{"url":null,"slug":"upb-acti-detecting-conspiracies-using-fine","title":"UPB @ ACTI: Detecting Conspiracies using fine tuned Sentence Transformers","date":"2023-09-28","arxiv_id":"2309.16275","repositories_listed":0,"syntology":null},{"url":null,"slug":"american-stories-a-large-scale-structured","title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers","date":"2023-08-24","arxiv_id":"2308.12477","repositories_listed":0,"syntology":null}],"syntology_records":13,"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":8,"papers_where_code_ran_first_page":"/task/topic-classification/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":"archive","page":2,"of":2,"url":"/task/topic-classification/papers/2","json":"/task/topic-classification/papers/2.json","rows":86},{"order":"ran","page":1,"of":1,"url":"/task/topic-classification/papers/ran/1","json":"/task/topic-classification/papers/ran/1.json","rows":8}],"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":"5f8d079c293a5e314651939a12be430778294150878e9ad31e80bb4f103ff0e8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}