{"attribution":{"source":"MIT AI Risk Repository, Domain Taxonomy of AI Risks v1 (MIT AI Risk Initiative)","license":"CC BY 4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","citation":"Slattery, P., Saeri, A. K., Grundy, E. A. C., Graham, J., Noetel, M., Uuk, R., Dao, J., Pour, S., Casper, S., & Thompson, N. (2025). The AI Risk Repository: A comprehensive meta-review, database, and taxonomy of risks from artificial intelligence. arXiv:2408.12622."},"exported_at":"2026-09-11"}
{"rows":[{"ev_id":"02.01.00","quick_ref":"Cui2024","paper_title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","level":"Risk Category","risk_category":"Harmful Content","risk_subcategory":null,"description":"\"The LLM-generated content sometimes contains biased, toxic, and private information\"","entity":"AI","intent":"Unintentional","timing":"Post-deployment","domain":1,"subdomain":"1.2"},{"ev_id":"02.01.02","quick_ref":"Cui2024","paper_title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","level":"Risk Sub-Category","risk_category":"Harmful Content","risk_subcategory":"Toxicity","description":"\"Toxicity means the generated content contains rude, disrespectful, and even illegal information\"","entity":"AI","intent":"Unintentional","timing":"Post-deployment","domain":1,"subdomain":"1.2"},{"ev_id":"02.08.01","quick_ref":"Cui2024","paper_title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","level":"Risk Sub-Category","risk_category":"Toxicity and Bias Tendencies","risk_subcategory":"Toxic Training Data","description":"\"Following previous studies [96], [97], toxic data in LLMs is defined as rude, disrespectful, or unreasonable language that is opposite to a polite, positive, and healthy language environment, including hate speech, offensive utterance, profanities, and threats [91].\"","entity":"AI","intent":"Unintentional","timing":"Pre-deployment","domain":1,"subdomain":"1.2"},{"ev_id":"02.11.00","quick_ref":"Cui2024","paper_title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","level":"Risk Category","risk_category":"Not-Suitable-for-Work (NSFW) Prompts","risk_subcategory":null,"description":"\"Inputting a prompt contain an unsafe topic (e.g., notsuitable-for-work (NSFW) content) by a benign user.\n\"","entity":"Human","intent":"Unintentional","timing":"Post-deployment","domain":1,"subdomain":"1.2"}]}