{"url":"/task/ai-and-safety","name":"AI and Safety","slug":"ai-and-safety","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":4,"papers_with_code":4,"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":5,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/salad-bench","name":"SALAD-Bench","full_name":"A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","num_papers_in_archive":18},{"url":"/dataset/clear-bias","name":"CLEAR-Bias","full_name":"Corpus for Linguistic Evaluation of Adversarial Robustness against Bias","num_papers_in_archive":2},{"url":"/dataset/hixstest","name":"HiXSTest","full_name":"Hindi XSTest","num_papers_in_archive":1},{"url":"/dataset/sgxstest","name":"SGXSTest","full_name":"Singapore XSTest","num_papers_in_archive":1},{"url":"/dataset/sudo-dataset","name":"SUDO Dataset","full_name":"","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":4,"of":4,"tagged_in_all":4,"items":[{"url":"/paper/sudo-rm-rf-agentic-security","title":"sudo rm -rf agentic_security","date":"2025-03-26","arxiv_id":"2503.20279","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/ferret-faster-and-effective-automated-red","title":"Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique","date":"2024-08-20","arxiv_id":"2408.10701","repositories_listed":1,"syntology":null},{"url":"/paper/walledeval-a-comprehensive-safety-evaluation","title":"WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models","date":"2024-08-07","arxiv_id":"2408.03837","repositories_listed":1,"syntology":null},{"url":"/paper/safety-arithmetic-a-framework-for-test-time","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","date":"2024-06-17","arxiv_id":"2406.11801","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}],"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"}}