{"url":"/task/argument-retrieval","name":"Argument Retrieval","slug":"argument-retrieval","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":14,"papers_with_code":9,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/beir","name":"BEIR","full_name":"Benchmarking IR","num_papers_in_archive":311},{"url":"/dataset/webis-touche-2020","name":"Webis-Touché-2020","full_name":"","num_papers_in_archive":2},{"url":"/dataset/finarg","name":"FinArg","full_name":"Financial Argument Mining","num_papers_in_archive":0}],"subtasks":[],"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":9,"of":9,"tagged_in_all":14,"items":[{"url":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","date":"2021-04-17","arxiv_id":"2104.08663","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/evaluating-fairness-in-argument-retrieval","title":"Evaluating Fairness in Argument Retrieval","date":"2021-08-23","arxiv_id":"2108.10442","repositories_listed":2,"syntology":null},{"url":"/paper/overview-of-perpectivearg2024-the-first","title":"Overview of PerpectiveArg2024: The First Shared Task on Perspective Argument Retrieval","date":"2024-07-29","arxiv_id":"2407.19670","repositories_listed":1,"syntology":null},{"url":"/paper/systematic-evaluation-of-neural-retrieval","title":"Systematic Evaluation of Neural Retrieval Models on the Touché 2020 Argument Retrieval Subset of BEIR","date":"2024-07-10","arxiv_id":"2407.07790","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-relevance-feedback-for","title":"Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking","date":"2022-10-19","arxiv_id":"2210.10695","repositories_listed":1,"syntology":null},{"url":"/paper/no-parameter-left-behind-how-distillation-and","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","date":"2022-06-06","arxiv_id":"2206.02873","repositories_listed":1,"syntology":null},{"url":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/diversity-aware-relevance-learning-for","title":"Diversity Aware Relevance Learning for Argument Search","date":"2020-11-04","arxiv_id":"2011.02177","repositories_listed":1,"syntology":null},{"url":"/paper/robust-argument-unit-recognition-and","title":"Fine-Grained Argument Unit Recognition and Classification","date":"2019-04-22","arxiv_id":"1904.09688","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"}}