{"url":"/task/ethics","name":"Ethics","slug":"ethics","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":832,"papers_with_code":100,"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":4,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/ethics-on-ethics","slug":"ethics-on-ethics","dataset":"Ethics","dataset_url":"/dataset/ethics-1","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RuGPT-3 Large","paper_title":"TAPE: Assessing Few-shot Russian Language Understanding","paper_url":"/paper/tape-assessing-few-shot-russian-language","paper_date":"2022-10-23","arxiv_id":"2210.12813","code_links":[{"title":"RussianNLP/TAPE","url":"https://github.com/RussianNLP/TAPE"}],"syntology":null}},{"leaderboard":"/sota/ethics-on-ethics-2","slug":"ethics-on-ethics-2","dataset":"Ethics (per ethics)","dataset_url":"/dataset/ethics-2","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Human benchmark","paper_title":"TAPE: Assessing Few-shot Russian Language Understanding","paper_url":"/paper/tape-assessing-few-shot-russian-language","paper_date":"2022-10-23","arxiv_id":"2210.12813","code_links":[{"title":"RussianNLP/TAPE","url":"https://github.com/RussianNLP/TAPE"}],"syntology":null}}],"datasets":[{"url":"/dataset/ethics-2","name":"Ethics (per ethics)","full_name":"","num_papers_in_archive":2},{"url":"/dataset/shadr","name":"SHADR","full_name":"sythetic SDoH Human Annotated Demographic Robustness dataset (SHADR)","num_papers_in_archive":1}],"subtasks":[{"url":"/task/business-ethics","name":"Business Ethics"},{"url":"/task/moral-disputes","name":"Moral Disputes"},{"url":"/task/moral-permissibility","name":"Moral Permissibility"},{"url":"/task/moral-scenarios","name":"Moral Scenarios"}],"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":30,"of":100,"tagged_in_all":832,"items":[{"url":"/paper/ego4d-around-the-world-in-3000-hours-of","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","date":"2021-10-13","arxiv_id":"2110.07058","repositories_listed":8,"syntology":{"n":15,"n_ran":4,"n_unverified":11,"n_pointer_only":2}},{"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/ethics-sheet-for-automatic-emotion","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","date":"2021-09-17","arxiv_id":"2109.08256","repositories_listed":3,"syntology":null},{"url":"/paper/ethics-sheets-for-ai-tasks","title":"Ethics Sheets for AI Tasks","date":"2021-07-02","arxiv_id":"2107.01183","repositories_listed":3,"syntology":null},{"url":"/paper/aligning-ai-with-shared-human-values","title":"Aligning AI With Shared Human Values","date":"2020-08-05","arxiv_id":"2008.02275","repositories_listed":3,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/comprehensive-assessment-of-jailbreak-attacks","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","date":"2024-02-08","arxiv_id":"2402.05668","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/trustllm-trustworthiness-in-large-language","title":"TrustLLM: Trustworthiness in Large Language Models","date":"2024-01-10","arxiv_id":"2401.05561","repositories_listed":2,"syntology":null},{"url":"/paper/ai-for-global-climate-cooperation-modeling","title":"AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N","date":"2022-08-15","arxiv_id":"2208.07004","repositories_listed":2,"syntology":null},{"url":"/paper/ethical-and-fairness-implications-of-model","title":"Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity","date":"2022-03-14","arxiv_id":"2203.07139","repositories_listed":2,"syntology":null},{"url":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","date":"2025-05-25","arxiv_id":"2505.19212","repositories_listed":1,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/2505-11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","date":"2025-05-16","arxiv_id":"2505.11454","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-distributive-justice-in-federated","title":"Achieving Distributive Justice in Federated Learning via Uncertainty Quantification","date":"2025-04-22","arxiv_id":"2504.15924","repositories_listed":1,"syntology":null},{"url":"/paper/surveying-professional-writers-on-ai","title":"Surveying Professional Writers on AI: Limitations, Expectations, and Fears","date":"2025-04-07","arxiv_id":"2504.05008","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-safety-of-japanese-large","title":"Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts","date":"2025-03-03","arxiv_id":"2503.01947","repositories_listed":1,"syntology":null},{"url":"/paper/toward-robust-non-transferable-learning-a","title":"Toward Robust Non-Transferable Learning: A Survey and Benchmark","date":"2025-02-19","arxiv_id":"2502.13593","repositories_listed":1,"syntology":null},{"url":"/paper/the-odyssey-of-the-fittest-can-agents-survive","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","date":"2025-02-08","arxiv_id":"2502.05442","repositories_listed":1,"syntology":null},{"url":"/paper/apple-an-applied-ethics-ontology-with-event","title":"ApplE: An Applied Ethics Ontology with Event Context","date":"2025-02-07","arxiv_id":"2502.05110","repositories_listed":1,"syntology":null},{"url":"/paper/bias-in-decision-making-for-ai-s-ethical","title":"Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude","date":"2025-01-17","arxiv_id":"2501.10484","repositories_listed":1,"syntology":null},{"url":"/paper/visual-large-language-models-for-generalized","title":"Visual Large Language Models for Generalized and Specialized Applications","date":"2025-01-06","arxiv_id":"2501.02765","repositories_listed":1,"syntology":null},{"url":"/paper/the-only-way-is-ethics-a-guide-to-ethical","title":"The Only Way is Ethics: A Guide to Ethical Research with Large Language Models","date":"2024-12-20","arxiv_id":"2412.16022","repositories_listed":1,"syntology":null},{"url":"/paper/a-history-of-philosophy-in-colombia-through","title":"A History of Philosophy in Colombia through Topic Modelling","date":"2024-12-05","arxiv_id":"2412.04236","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-generalization-risk-reduction-for","title":"Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimation","date":"2024-11-18","arxiv_id":"2411.11256","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-large-language-models-generated","title":"Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework","date":"2024-10-18","arxiv_id":"2410.14231","repositories_listed":1,"syntology":null},{"url":"/paper/data-defenses-against-large-language-models","title":"Data Defenses Against Large Language Models","date":"2024-10-17","arxiv_id":"2410.13138","repositories_listed":1,"syntology":null},{"url":"/paper/ethics-whitepaper-whitepaper-on-ethical","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","date":"2024-10-17","arxiv_id":"2410.19812","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-state-of-nlp-approaches-to-modeling","title":"On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook","date":"2024-10-11","arxiv_id":"2410.08793","repositories_listed":1,"syntology":null},{"url":"/paper/triage-ethical-benchmarking-of-ai-models","title":"TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations","date":"2024-10-10","arxiv_id":"2410.18991","repositories_listed":1,"syntology":null},{"url":"/paper/xtrust-on-the-multilingual-trustworthiness-of","title":"XTRUST: On the Multilingual Trustworthiness of Large Language Models","date":"2024-09-24","arxiv_id":"2409.15762","repositories_listed":1,"syntology":null},{"url":"/paper/ram2c-a-liberal-arts-educational-chatbot","title":"RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration","date":"2024-09-23","arxiv_id":"2409.15461","repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}