{"id":21571515,"url":"https://github.com/leondz/lm_risk_cards","last_synced_at":"2025-07-01T09:31:39.168Z","repository":{"id":151512547,"uuid":"577952235","full_name":"leondz/lm_risk_cards","owner":"leondz","description":"Risks and targets for assessing LLMs \u0026 LLM vulnerabilities","archived":false,"fork":false,"pushed_at":"2024-05-27T15:07:32.000Z","size":88,"stargazers_count":30,"open_issues_count":0,"forks_count":8,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-03-24T13:02:55.176Z","etag":null,"topics":["llm","llm-security","red-teaming","security","vulnerability"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2303.18190","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/leondz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-12-13T22:51:35.000Z","updated_at":"2024-12-20T20:42:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"f0d2b058-5297-416c-a5b1-d6f81d67b98b","html_url":"https://github.com/leondz/lm_risk_cards","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leondz%2Flm_risk_cards","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leondz%2Flm_risk_cards/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leondz%2Flm_risk_cards/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leondz%2Flm_risk_cards/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/leondz","download_url":"https://codeload.github.com/leondz/lm_risk_cards/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248233936,"owners_count":21069493,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["llm","llm-security","red-teaming","security","vulnerability"],"created_at":"2024-11-24T11:16:34.196Z","updated_at":"2025-04-10T14:21:01.029Z","avatar_url":"https://github.com/leondz.png","language":"Python","funding_links":[],"categories":["Community and Official Guidance Resources"],"sub_categories":["Community Frameworks and Guidance"],"readme":"# Language Model Risk Cards: Starter Set\n\nA set of Language Model Risk cards for assessing a language model use case. To use these:\n\n* Choose what use-case, model, and interface is to be assessed\n* Select which of these risk cards is relevant in the given use-case scenario\n* Recruit people to do the assessment\n* For each risk card,\n  * Design how one will probe the model, and for how long\n  * Try to provoke the described behaviour from the language model, using your own prompts\n  * Record all inputs and outputs\n* Compile an assessment report\n\nFull details are given in the paper: [Assessing Language Model Deployment with Risk Cards](https://arxiv.org/abs/2303.18190) (2023), *Leon Derczynski, Hannah Rose Kirk, Vidhisha Balachandran, Sachin Kumar, Yulia Tsvetkov, M. R. Leiser, Saif Mohammad*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleondz%2Flm_risk_cards","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fleondz%2Flm_risk_cards","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleondz%2Flm_risk_cards/lists"}