{"url":"/task/moral-scenarios","name":"Moral Scenarios","slug":"moral-scenarios","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":17,"papers_with_code":9,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/moral-scenarios-on-big-bench","slug":"moral-scenarios-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=5)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/ollabench-v-0-2","name":"OllaBench v.0.2","full_name":"OllaBench for Interdependent Cybersecurity v.0.2","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/ethics","name":"Ethics"}],"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":17,"items":[{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/halo-hierarchical-autonomous-logic-oriented","title":"HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems","date":"2025-05-17","arxiv_id":"2505.13516","repositories_listed":1,"syntology":null},{"url":"/paper/measurement-of-llm-s-philosophies-of-human","title":"Measurement of LLM's Philosophies of Human Nature","date":"2025-04-03","arxiv_id":"2504.02304","repositories_listed":1,"syntology":null},{"url":"/paper/m-3-oralbench-a-multimodal-moral-benchmark","title":"M$^3$oralBench: A MultiModal Moral Benchmark for LVLMs","date":"2024-12-30","arxiv_id":"2412.20718","repositories_listed":1,"syntology":null},{"url":"/paper/cmoraleval-a-moral-evaluation-benchmark-for","title":"CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models","date":"2024-08-19","arxiv_id":"2408.09819","repositories_listed":1,"syntology":null},{"url":"/paper/sage-evaluating-moral-consistency-in-large","title":"SaGE: Evaluating Moral Consistency in Large Language Models","date":"2024-02-21","arxiv_id":"2402.13709","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/moka-moral-knowledge-augmentation-for-moral","title":"MOKA: Moral Knowledge Augmentation for Moral Event Extraction","date":"2023-11-16","arxiv_id":"2311.09733","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-moral-beliefs-encoded-in-llms-1","title":"Evaluating the Moral Beliefs Encoded in LLMs","date":"2023-07-26","arxiv_id":"2307.14324","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/oops-did-i-just-say-that-testing-and","title":"\"Oops, Did I Just Say That?\" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process","date":"2023-05-04","arxiv_id":"2305.02626","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"}}