{"url":"/task/dialogue-safety-prediction","name":"Dialogue Safety Prediction","slug":"dialogue-safety-prediction","description_markdown":"Determine the safety of a given dialogue context.","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":3,"papers_with_code":3,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/dialogue-safety-prediction-on-rt-inod","slug":"dialogue-safety-prediction-on-rt-inod","dataset":"rt-inod-jailbreaking","dataset_url":"/dataset/rt-inod-jailbreaking","rows_in_archive":5,"metrics":["Best-of"],"first_row_in_archive_order":{"model":"Baseline","paper_title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","paper_url":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","paper_date":"2024-04-15","arxiv_id":"2404.09785","code_links":[{"title":"innodatalabs/innodata-llm-safety","url":"https://github.com/innodatalabs/innodata-llm-safety"}],"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/dialogue-safety-prediction-on-prosocialdialog","slug":"dialogue-safety-prediction-on-prosocialdialog","dataset":"ProsocialDialog","dataset_url":"/dataset/prosocialdialog","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Canary","paper_title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","paper_url":"/paper/prosocialdialog-a-prosocial-backbone-for","paper_date":"2022-05-25","arxiv_id":"2205.12688","code_links":[{"title":"skywalker023/prosocial-dialog","url":"https://github.com/skywalker023/prosocial-dialog"}],"syntology":null}}],"datasets":[{"url":"/dataset/prosocialdialog","name":"ProsocialDialog","full_name":"","num_papers_in_archive":13},{"url":"/dataset/rt-inod-jailbreaking","name":"rt-inod-jailbreaking","full_name":"Red Teaming Innodata Jailbreaking","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/dialogue-understanding","name":"Dialogue Understanding"}],"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":3,"of":3,"tagged_in_all":3,"items":[{"url":"/paper/alert-a-comprehensive-benchmark-for-assessing","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","date":"2024-04-06","arxiv_id":"2404.08676","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","date":"2024-04-15","arxiv_id":"2404.09785","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/prosocialdialog-a-prosocial-backbone-for","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","date":"2022-05-25","arxiv_id":"2205.12688","repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}