{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":9,"rows_per_page":100,"shown":100,"of":832,"of_with_code":100,"tagged_in_all":832,"counts":{"archive_papers_tagged":832,"with_a_code_link":100,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":832,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/ego4d-around-the-world-in-3000-hours-of","slug":"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":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ego4d-around-the-world-in-3000-hours-of#ran","syntology_url":"https://syntology.ai/paper/2110.07058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07058"}},"official":{"repos":["facebookresearch/Ego4d"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/aligning-ai-with-shared-human-values#ran","syntology_url":"https://syntology.ai/paper/2008.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02275"}},"official":{"repos":["hendrycks/ethics"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/multilingual-trolley-problems-for-language","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multilingual-trolley-problems-for-language#ran","syntology_url":"https://syntology.ai/paper/2407.02273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02273"}},"official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/comprehensive-assessment-of-jailbreak-attacks","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/comprehensive-assessment-of-jailbreak-attacks#ran","syntology_url":"https://syntology.ai/paper/2402.05668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05668"}},"official":{"repos":["TrustAIRLab/Comprehensive_Jailbreak_Assessment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/trustllm-trustworthiness-in-large-language","slug":"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","slug":"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","slug":"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","slug":"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":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in#ran","syntology_url":"https://syntology.ai/paper/2505.19212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19212"}},"official":{"repos":["sbackmann/moralsim"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/2505-11454","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":"/paper/has-multimodal-learning-delivered-universal","slug":"has-multimodal-learning-delivered-universal","title":"Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey","date":"2024-08-23","arxiv_id":"2408.12880","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-labels-aligning-large-language-models","slug":"beyond-labels-aligning-large-language-models","title":"Beyond Labels: Aligning Large Language Models with Human-like Reasoning","date":"2024-08-20","arxiv_id":"2408.11879","repositories_listed":1,"syntology":null},{"url":"/paper/acl-ready-rag-based-assistant-for-the-acl","slug":"acl-ready-rag-based-assistant-for-the-acl","title":"ACL Ready: RAG Based Assistant for the ACL Checklist","date":"2024-08-07","arxiv_id":"2408.04675","repositories_listed":1,"syntology":null},{"url":"/paper/psycollm-enhancing-llm-for-psychological","slug":"psycollm-enhancing-llm-for-psychological","title":"PsycoLLM: Enhancing LLM for Psychological Understanding and Evaluation","date":"2024-07-08","arxiv_id":"2407.05721","repositories_listed":1,"syntology":null},{"url":"/paper/some-issues-in-predictive-ethics-modeling-an","slug":"some-issues-in-predictive-ethics-modeling-an","title":"Some Issues in Predictive Ethics Modeling: An Annotated Contrast Set of \"Moral Stories\"","date":"2024-07-07","arxiv_id":"2407.05244","repositories_listed":1,"syntology":null},{"url":"/paper/moralbench-moral-evaluation-of-llms","slug":"moralbench-moral-evaluation-of-llms","title":"MoralBench: Moral Evaluation of LLMs","date":"2024-06-06","arxiv_id":"2406.04428","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-and-steering-the-moral-compass-of","slug":"exploring-and-steering-the-moral-compass-of","title":"Exploring and steering the moral compass of Large Language Models","date":"2024-05-27","arxiv_id":"2405.17345","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-and-steering-the-moral-compass-of#ran","syntology_url":"https://syntology.ai/paper/2405.17345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17345"}},"official":{"repos":["atlaie/ethical-llms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-large-language-models-for-3","slug":"a-survey-on-large-language-models-for-3","title":"A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law","date":"2024-05-02","arxiv_id":"2405.01769","repositories_listed":1,"syntology":null},{"url":"/paper/more-rlhf-more-trust-on-the-impact-of-human","slug":"more-rlhf-more-trust-on-the-impact-of-human","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","date":"2024-04-29","arxiv_id":"2404.18870","repositories_listed":1,"syntology":null},{"url":"/paper/a-taxation-perspective-for-fair-re-ranking","slug":"a-taxation-perspective-for-fair-re-ranking","title":"A Taxation Perspective for Fair Re-ranking","date":"2024-04-27","arxiv_id":"2404.17826","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-emotions-and-ethics-with-large","slug":"modeling-emotions-and-ethics-with-large","title":"Modeling Emotions and Ethics with Large Language Models","date":"2024-04-15","arxiv_id":"2404.13071","repositories_listed":1,"syntology":null},{"url":"/paper/risks-from-language-models-for-automated","slug":"risks-from-language-models-for-automated","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","date":"2024-04-02","arxiv_id":"2406.11852","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safe-and-aligned-large-language","slug":"towards-safe-and-aligned-large-language","title":"MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models","date":"2024-03-06","arxiv_id":"2403.03744","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/towards-safe-and-aligned-large-language#ran","syntology_url":"https://syntology.ai/paper/2403.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03744"}},"official":{"repos":["ai4life-group/med-safety-bench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/newsbench-systematic-evaluation-of-llms-for","slug":"newsbench-systematic-evaluation-of-llms-for","title":"NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism","date":"2024-02-29","arxiv_id":"2403.00862","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/newsbench-systematic-evaluation-of-llms-for#ran","syntology_url":"https://syntology.ai/paper/2403.00862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00862"}},"official":{"repos":["iaar-shanghai/newsbench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/morality-is-non-binary-building-a-pluralist","slug":"morality-is-non-binary-building-a-pluralist","title":"Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning","date":"2024-01-30","arxiv_id":"2401.17228","repositories_listed":1,"syntology":null},{"url":"/paper/e-eval-a-comprehensive-chinese-k-12-education","slug":"e-eval-a-comprehensive-chinese-k-12-education","title":"E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models","date":"2024-01-29","arxiv_id":"2401.15927","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/e-eval-a-comprehensive-chinese-k-12-education#ran","syntology_url":"https://syntology.ai/paper/2401.15927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15927"}},"official":{"repos":["ai-edu-lab/e-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/informed-ai-regulation-comparing-the-ethical","slug":"informed-ai-regulation-comparing-the-ethical","title":"Informed AI Regulation: Comparing the Ethical Frameworks of Leading LLM Chatbots Using an Ethics-Based Audit to Assess Moral Reasoning and Normative Values","date":"2024-01-09","arxiv_id":"2402.01651","repositories_listed":1,"syntology":null},{"url":"/paper/data-centric-foundation-models-in","slug":"data-centric-foundation-models-in","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","date":"2024-01-04","arxiv_id":"2401.02458","repositories_listed":1,"syntology":null},{"url":"/paper/how-trustworthy-are-open-source-llms-an","slug":"how-trustworthy-are-open-source-llms-an","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","date":"2023-11-15","arxiv_id":"2311.09447","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/how-trustworthy-are-open-source-llms-an#ran","syntology_url":"https://syntology.ai/paper/2311.09447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09447"}},"official":{"repos":["osu-nlp-group/eval-llm-trust"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-human-action-recognition","slug":"learning-human-action-recognition","title":"Learning Human Action Recognition Representations Without Real Humans","date":"2023-11-10","arxiv_id":"2311.06231","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-human-action-recognition#ran","syntology_url":"https://syntology.ai/paper/2311.06231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06231"}},"official":{"repos":["howardzh01/ppma"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-effective-paraphrasing-for","slug":"towards-effective-paraphrasing-for","title":"Towards Effective Paraphrasing for Information Disguise","date":"2023-11-08","arxiv_id":"2311.05018","repositories_listed":1,"syntology":null},{"url":"/paper/an-integrative-survey-on-mental-health","slug":"an-integrative-survey-on-mental-health","title":"An Integrative Survey on Mental Health Conversational Agents to Bridge Computer Science and Medical Perspectives","date":"2023-10-25","arxiv_id":"2310.17017","repositories_listed":1,"syntology":null},{"url":"/paper/cleftgan-adapting-a-style-based-generative","slug":"cleftgan-adapting-a-style-based-generative","title":"CleftGAN: Adapting A Style-Based Generative Adversarial Network To Create Images Depicting Cleft Lip Deformity","date":"2023-10-12","arxiv_id":"2310.07969","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-large-language-models-for","slug":"a-survey-of-large-language-models-for","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","date":"2023-10-09","arxiv_id":"2310.05694","repositories_listed":1,"syntology":null},{"url":"/paper/ealm-introducing-multidimensional-ethical","slug":"ealm-introducing-multidimensional-ethical","title":"EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval","date":"2023-10-02","arxiv_id":"2310.00970","repositories_listed":1,"syntology":null},{"url":"/paper/cats-conditional-adversarial-trajectory","slug":"cats-conditional-adversarial-trajectory","title":"CATS: Conditional Adversarial Trajectory Synthesis for Privacy-Preserving Trajectory Data Publication Using Deep Learning Approaches","date":"2023-09-20","arxiv_id":"2309.11587","repositories_listed":1,"syntology":null},{"url":"/paper/sight-beyond-text-multi-modal-training","slug":"sight-beyond-text-multi-modal-training","title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","date":"2023-09-13","arxiv_id":"2309.07120","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sight-beyond-text-multi-modal-training#ran","syntology_url":"https://syntology.ai/paper/2309.07120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07120"}},"official":{"repos":["ucsc-vlaa/sight-beyond-text"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ted-spad-temporal-distinctiveness-for-self","slug":"ted-spad-temporal-distinctiveness-for-self","title":"TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection","date":"2023-08-21","arxiv_id":"2308.11072","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ted-spad-temporal-distinctiveness-for-self#ran","syntology_url":"https://syntology.ai/paper/2308.11072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11072"}},"official":{"repos":["ucf-crcv/ted-spad"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gpt-4-is-too-smart-to-be-safe-stealthy-chat","slug":"gpt-4-is-too-smart-to-be-safe-stealthy-chat","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","date":"2023-08-12","arxiv_id":"2308.06463","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-is-too-smart-to-be-safe-stealthy-chat#ran","syntology_url":"https://syntology.ai/paper/2308.06463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06463"}},"official":{"repos":["robustnlp/cipherchat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-to-identify-social","slug":"large-language-models-to-identify-social","title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records","date":"2023-08-11","arxiv_id":"2308.06354","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-language-models-to-identify-social#ran","syntology_url":"https://syntology.ai/paper/2308.06354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06354"}},"official":{"repos":["aim-harvard/sdoh"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/getting-pwn-d-by-ai-penetration-testing-with","slug":"getting-pwn-d-by-ai-penetration-testing-with","title":"Getting pwn'd by AI: Penetration Testing with Large Language Models","date":"2023-07-24","arxiv_id":"2308.00121","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/getting-pwn-d-by-ai-penetration-testing-with#ran","syntology_url":"https://syntology.ai/paper/2308.00121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00121"}},"official":{"repos":["ipa-lab/hackingBuddyGPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/decorrelation-using-optimal-transport","slug":"decorrelation-using-optimal-transport","title":"Decorrelation using Optimal Transport","date":"2023-07-11","arxiv_id":"2307.05187","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-evaluation-of-large-language","slug":"a-survey-on-evaluation-of-large-language","title":"A Survey on Evaluation of Large Language Models","date":"2023-07-06","arxiv_id":"2307.03109","repositories_listed":1,"syntology":null},{"url":"/paper/how-can-recommender-systems-benefit-from","slug":"how-can-recommender-systems-benefit-from","title":"How Can Recommender Systems Benefit from Large Language Models: A Survey","date":"2023-06-09","arxiv_id":"2306.05817","repositories_listed":1,"syntology":null},{"url":"/paper/brain-tumor-segmentation-using-synthetic-mr","slug":"brain-tumor-segmentation-using-synthetic-mr","title":"Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models","date":"2023-06-05","arxiv_id":"2306.02986","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/brain-tumor-segmentation-using-synthetic-mr#ran","syntology_url":"https://syntology.ai/paper/2306.02986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02986"}},"official":{"repos":["muhamadusman/assist"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/responsible-design-patterns-for-machine","slug":"responsible-design-patterns-for-machine","title":"Responsible Design Patterns for Machine Learning Pipelines","date":"2023-05-31","arxiv_id":"2306.01788","repositories_listed":1,"syntology":null},{"url":"/paper/uncertain-machine-ethical-decisions-using","slug":"uncertain-machine-ethical-decisions-using","title":"Uncertain Machine Ethical Decisions Using Hypothetical Retrospection","date":"2023-05-02","arxiv_id":"2305.01424","repositories_listed":1,"syntology":null},{"url":"/paper/a-group-specific-approach-to-nlp-for-hate","slug":"a-group-specific-approach-to-nlp-for-hate","title":"A Group-Specific Approach to NLP for Hate Speech Detection","date":"2023-04-21","arxiv_id":"2304.11223","repositories_listed":1,"syntology":null},{"url":"/paper/thorny-roses-investigating-the-dual-use","slug":"thorny-roses-investigating-the-dual-use","title":"Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing","date":"2023-04-17","arxiv_id":"2304.08315","repositories_listed":1,"syntology":null},{"url":"/paper/raft-reward-ranked-finetuning-for-generative","slug":"raft-reward-ranked-finetuning-for-generative","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","date":"2023-04-13","arxiv_id":"2304.06767","repositories_listed":1,"syntology":null},{"url":"/paper/do-the-rewards-justify-the-means-measuring","slug":"do-the-rewards-justify-the-means-measuring","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","date":"2023-04-06","arxiv_id":"2304.03279","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-the-rewards-justify-the-means-measuring#ran","syntology_url":"https://syntology.ai/paper/2304.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03279"}},"official":{"repos":["aypan17/machiavelli"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synthetically-generated-text-for-supervised","slug":"synthetically-generated-text-for-supervised","title":"Synthetically generated text for supervised text analysis","date":"2023-03-28","arxiv_id":"2303.16028","repositories_listed":1,"syntology":null},{"url":"/paper/ai-ethics-on-blockchain-topic-analysis-on","slug":"ai-ethics-on-blockchain-topic-analysis-on","title":"AI Ethics on Blockchain: Topic Analysis on Twitter Data for Blockchain Security","date":"2022-12-14","arxiv_id":"2212.06951","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-visual-commonsense-immorality","slug":"zero-shot-visual-commonsense-immorality","title":"Zero-shot Visual Commonsense Immorality Prediction","date":"2022-11-10","arxiv_id":"2211.05521","repositories_listed":1,"syntology":null},{"url":"/paper/mt-geneval-a-counterfactual-and-contextual","slug":"mt-geneval-a-counterfactual-and-contextual","title":"MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation","date":"2022-11-02","arxiv_id":"2211.01355","repositories_listed":1,"syntology":null},{"url":"/paper/tape-assessing-few-shot-russian-language","slug":"tape-assessing-few-shot-russian-language","title":"TAPE: Assessing Few-shot Russian Language Understanding","date":"2022-10-23","arxiv_id":"2210.12813","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-understanding-and-visualizing","slug":"a-framework-for-understanding-and-visualizing","title":"A Framework for Understanding and Visualizing Strategies of RL Agents","date":"2022-08-17","arxiv_id":"2208.08552","repositories_listed":1,"syntology":null},{"url":"/paper/automated-kantian-ethics-a-faithful","slug":"automated-kantian-ethics-a-faithful","title":"Automated Kantian Ethics: A Faithful Implementation","date":"2022-07-20","arxiv_id":"2207.10152","repositories_listed":1,"syntology":null},{"url":"/paper/worldwide-ai-ethics-a-review-of-200","slug":"worldwide-ai-ethics-a-review-of-200","title":"Worldwide AI Ethics: a review of 200 guidelines and recommendations for AI governance","date":"2022-06-23","arxiv_id":"2206.11922","repositories_listed":1,"syntology":null},{"url":"/paper/what-are-people-talking-about-in","slug":"what-are-people-talking-about-in","title":"What are People Talking about in #BlackLivesMatter and #StopAsianHate? Exploring and Categorizing Twitter Topics Emerging in Online Social Movements through the Latent Dirichlet Allocation Model","date":"2022-05-29","arxiv_id":"2205.14725","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-multi-stakeholder-value-based","slug":"towards-a-multi-stakeholder-value-based","title":"Towards a multi-stakeholder value-based assessment framework for algorithmic systems","date":"2022-05-09","arxiv_id":"2205.04525","repositories_listed":1,"syntology":null},{"url":"/paper/moral-aligning-ai-with-human-norms-through","slug":"moral-aligning-ai-with-human-norms-through","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","date":"2021-12-30","arxiv_id":"2201.00012","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/moral-aligning-ai-with-human-norms-through#ran","syntology_url":"https://syntology.ai/paper/2201.00012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00012"}},"official":{"repos":["mlpeschl/moral_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/artificial-intelligence-ethics-and-safety","slug":"artificial-intelligence-ethics-and-safety","title":"Artificial Intelligence Ethics and Safety: practical tools for creating \"good\" models","date":"2021-12-14","arxiv_id":"2112.11208","repositories_listed":1,"syntology":null},{"url":"/paper/delphi-towards-machine-ethics-and-norms","slug":"delphi-towards-machine-ethics-and-norms","title":"Can Machines Learn Morality? The Delphi Experiment","date":"2021-10-14","arxiv_id":"2110.07574","repositories_listed":1,"syntology":null},{"url":"/paper/pass-an-imagenet-replacement-for-self","slug":"pass-an-imagenet-replacement-for-self","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","date":"2021-09-27","arxiv_id":"2109.13228","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pass-an-imagenet-replacement-for-self#ran","syntology_url":"https://syntology.ai/paper/2109.13228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13228"}},"official":{"repos":["yukimasano/PASS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/a-logic-based-multi-agent-system-for-ethical","slug":"a-logic-based-multi-agent-system-for-ethical","title":"A Logic-based Multi-agent System for Ethical Monitoring and Evaluation of Dialogues","date":"2021-09-17","arxiv_id":"2109.08294","repositories_listed":1,"syntology":null},{"url":"/paper/ethical-advice-taker-do-language-models","slug":"ethical-advice-taker-do-language-models","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","date":"2021-06-02","arxiv_id":"2106.01465","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ethical-advice-taker-do-language-models#ran","syntology_url":"https://syntology.ai/paper/2106.01465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01465"}},"official":{"repos":["allenai/ethical-interventions"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/verb-visualizing-and-interpreting-bias","slug":"verb-visualizing-and-interpreting-bias","title":"VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations","date":"2021-04-06","arxiv_id":"2104.02797","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-revisions-quality-assessment-of","slug":"learning-from-revisions-quality-assessment-of","title":"Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale","date":"2021-01-25","arxiv_id":"2101.10250","repositories_listed":1,"syntology":null},{"url":"/paper/synthesising-clinically-realistic-chest-x","slug":"synthesising-clinically-realistic-chest-x","title":"Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs","date":"2020-10-07","arxiv_id":"2010.03975","repositories_listed":1,"syntology":null},{"url":"/paper/scruples-a-corpus-of-community-ethical","slug":"scruples-a-corpus-of-community-ethical","title":"Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes","date":"2020-08-20","arxiv_id":"2008.09094","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scruples-a-corpus-of-community-ethical#ran","syntology_url":"https://syntology.ai/paper/2008.09094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09094"}},"official":{"repos":["allenai/scruples"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-recommendation-and-risk-classification","slug":"a-recommendation-and-risk-classification","title":"A Recommendation and Risk Classification System for Connecting Rough Sleepers to Essential Outreach Services","date":"2020-07-30","arxiv_id":"2007.15326","repositories_listed":1,"syntology":null},{"url":"/paper/deontological-ethics-by-monotonicity-shape","slug":"deontological-ethics-by-monotonicity-shape","title":"Deontological Ethics By Monotonicity Shape Constraints","date":"2020-01-31","arxiv_id":"2001.11990","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-software-engineering-for-ai-enabled","slug":"teaching-software-engineering-for-ai-enabled","title":"Teaching Software Engineering for AI-Enabled Systems","date":"2020-01-18","arxiv_id":"2001.06691","repositories_listed":1,"syntology":null},{"url":"/paper/mining-disinformation-and-fake-news-concepts","slug":"mining-disinformation-and-fake-news-concepts","title":"Mining Disinformation and Fake News: Concepts, Methods, and Recent Advancements","date":"2020-01-02","arxiv_id":"2001.00623","repositories_listed":1,"syntology":null},{"url":"/paper/towards-empathic-deep-q-learning","slug":"towards-empathic-deep-q-learning","title":"Towards Empathic Deep Q-Learning","date":"2019-06-26","arxiv_id":"1906.10918","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-empathic-deep-q-learning#ran","syntology_url":"https://syntology.ai/paper/1906.10918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10918"}},"official":{"repos":["bartbussmann/EmpathicDQN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-measuring-gender-bias-in-translation-of","slug":"on-measuring-gender-bias-in-translation-of","title":"On Measuring Gender Bias in Translation of Gender-neutral Pronouns","date":"2019-05-28","arxiv_id":"1905.11684","repositories_listed":1,"syntology":null},{"url":"/paper/defining-a-sandbox-for-responsible-ai","slug":"defining-a-sandbox-for-responsible-ai","title":"Defining a Sandbox for Responsible AI","date":"2018-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-low-cost-ethics-shaping-approach-for","slug":"a-low-cost-ethics-shaping-approach-for","title":"A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents","date":"2017-12-12","arxiv_id":"1712.04172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-low-cost-ethics-shaping-approach-for#ran","syntology_url":"https://syntology.ai/paper/1712.04172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.04172"}},"official":null}},{"url":"/paper/semantics-derived-automatically-from-language","slug":"semantics-derived-automatically-from-language","title":"Semantics derived automatically from language corpora contain human-like biases","date":"2016-08-25","arxiv_id":"1608.07187","repositories_listed":1,"syntology":null}],"syntology_records":24,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/task/ethics/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":9,"url":"/task/ethics/papers/2","json":"/task/ethics/papers/2.json","rows":100},{"order":"archive","page":3,"of":9,"url":"/task/ethics/papers/3","json":"/task/ethics/papers/3.json","rows":100},{"order":"archive","page":4,"of":9,"url":"/task/ethics/papers/4","json":"/task/ethics/papers/4.json","rows":100},{"order":"archive","page":5,"of":9,"url":"/task/ethics/papers/5","json":"/task/ethics/papers/5.json","rows":100},{"order":"archive","page":6,"of":9,"url":"/task/ethics/papers/6","json":"/task/ethics/papers/6.json","rows":100},{"order":"archive","page":7,"of":9,"url":"/task/ethics/papers/7","json":"/task/ethics/papers/7.json","rows":100},{"order":"archive","page":8,"of":9,"url":"/task/ethics/papers/8","json":"/task/ethics/papers/8.json","rows":100},{"order":"archive","page":9,"of":9,"url":"/task/ethics/papers/9","json":"/task/ethics/papers/9.json","rows":32},{"order":"ran","page":1,"of":1,"url":"/task/ethics/papers/ran/1","json":"/task/ethics/papers/ran/1.json","rows":22}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"214f4fa9ea0510ba23363de9fc61c5cf8525ceaf5dcdac9e6ac89a5ac1742a48","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}