{"url":"/task/probing-language-models","name":"Probing Language Models","slug":"probing-language-models","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":20,"papers_with_code":11,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":[{"leaderboard":"/sota/probing-language-models-on-kamel","slug":"probing-language-models-on-kamel","dataset":"KAMEL","dataset_url":"/dataset/kamel","rows_in_archive":1,"metrics":["Average F1"],"first_row_in_archive_order":{"model":"OPT-13b","paper_title":"KAMEL : Knowledge Analysis with Multitoken Entities in Language Models","paper_url":"/paper/kamel-knowledge-analysis-with-multitoken","paper_date":"2022-11-01","arxiv_id":null,"code_links":[{"title":"JanKalo/KAMEL","url":"https://github.com/JanKalo/KAMEL"}],"syntology":null}}],"datasets":[{"url":"/dataset/biolama","name":"BioLAMA","full_name":"","num_papers_in_archive":14},{"url":"/dataset/kamel","name":"KAMEL","full_name":"Knowledge Analysis with Multitoken Entities in Language Models","num_papers_in_archive":6},{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1}],"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":11,"of":11,"tagged_in_all":20,"items":[{"url":"/paper/universal-and-independent-multilingual","title":"Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation","date":"2022-10-24","arxiv_id":"2210.13236","repositories_listed":2,"syntology":null},{"url":"/paper/probing-language-models-on-their-knowledge","title":"Probing Language Models on Their Knowledge Source","date":"2024-10-08","arxiv_id":"2410.05817","repositories_listed":1,"syntology":null},{"url":"/paper/probing-language-models-for-pre-training-data","title":"Probing Language Models for Pre-training Data Detection","date":"2024-06-03","arxiv_id":"2406.01333","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/unveiling-llms-the-evolution-of-latent","title":"Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph","date":"2024-04-04","arxiv_id":"2404.03623","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/probing-representations-for-document-level","title":"Probing Representations for Document-level Event Extraction","date":"2023-10-23","arxiv_id":"2310.15316","repositories_listed":1,"syntology":null},{"url":"/paper/kamel-knowledge-analysis-with-multitoken","title":"KAMEL : Knowledge Analysis with Multitoken Entities in Language Models","date":"2022-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/discontinuous-constituency-and-bert-a-case-1","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","date":"2022-03-02","arxiv_id":"2203.01063","repositories_listed":1,"syntology":null},{"url":"/paper/the-neural-architecture-of-language","title":"The neural architecture of language: Integrative modeling converges on predictive processing","date":"2021-11-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/probing-language-models-for-understanding-of","title":"Probing Language Models for Understanding of Temporal Expressions","date":"2021-10-03","arxiv_id":"2110.01113","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/probing-toxic-content-in-large-pre-trained","title":"Probing Toxic Content in Large Pre-Trained Language Models","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-gender-bias-towards-politicians","title":"Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models","date":"2021-04-15","arxiv_id":"2104.07505","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"}}