{"id":20779476,"url":"https://github.com/freedomintelligence/freshbench","last_synced_at":"2026-03-02T04:03:57.585Z","repository":{"id":216623888,"uuid":"741816821","full_name":"FreedomIntelligence/FreshBench","owner":"FreedomIntelligence","description":null,"archived":false,"fork":false,"pushed_at":"2025-02-13T08:54:27.000Z","size":19804,"stargazers_count":6,"open_issues_count":1,"forks_count":0,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-11-10T00:21:04.922Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/FreedomIntelligence.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,"zenodo":null}},"created_at":"2024-01-11T07:06:19.000Z","updated_at":"2025-10-31T12:09:28.000Z","dependencies_parsed_at":"2024-01-12T12:31:01.108Z","dependency_job_id":"36f45266-9734-43da-9d4c-7d2ad683bfb6","html_url":"https://github.com/FreedomIntelligence/FreshBench","commit_stats":null,"previous_names":["freedomintelligence/fresh_eval","freedomintelligence/freshbench"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/FreedomIntelligence/FreshBench","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FFreshBench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FFreshBench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FFreshBench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FFreshBench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FreedomIntelligence","download_url":"https://codeload.github.com/FreedomIntelligence/FreshBench/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FFreshBench/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29992286,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T01:47:34.672Z","status":"online","status_checked_at":"2026-03-02T02:00:07.342Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2024-11-17T13:28:07.620Z","updated_at":"2026-03-02T04:03:57.544Z","avatar_url":"https://github.com/FreedomIntelligence.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n#### about the prediction data\nAt `/GoodJudgeOpen_crawler`\n\n\nThere is a readme.md and a pipeline.sh.\n\nYou can crawl the data incrementally using playwright by yourself, then you can update the current gjo file from crawler.\n\n```\nbase_path=\"./\"\ncurrent_gjo_file_path=\"${base_path}test/raw_question/gjo_transformed_questions_no_output.jsonl\"\ngjo_raw_crawl_file_path=\"${base_path}GoodJudgeOpen_crawler/gjo.json\"\n\npython update_from_crawl.py \\\n    --gjo_raw_crawl_file_path \"$gjo_raw_crawl_file_path\" \\\n    --current_gjo_file_path \"$current_gjo_file_path\"\n```\nThis updates the gjo questions in gjo_raw_crawl_file_path: by default `test/raw_question/gjo_transformed_questions_no_output.jsonl`\n\n\n### Letting models answer and judge the choice incrementally\n\n\n#### online:\nfill /script/base-url.txt and /script/api-key.txt\n\nfill the model names in `pipeline_api.sh`\n\n`bash ./pipeline_api.sh`\n\n#### local:\n\nfill the model names in `pipeline_local.sh`\n\n`bash ./pipeline_local.sh`\n\n### answer will be at /answer_csv/\u003cmodel_name\u003e.csv\n\n\n### classify Nostalgia and Neophilia\nspecify the periods in analysis/acc_p1p2.py and analysis/acc_p1p2_T2.py, they test the two hyposis, make sure the time_intervals_dic are the same, [(-80, -60), (-20, 0)] means comparing the accuracy during 80 to 60 months before model release and accuracy during the 20 months before release.\n```\ntime_intervals_dic = {  \n                      '[(-80, -60), (-20, 0)]':[(-80, -60), (-20, 0)],\n                      '[(-60, -40), (-20, 0)]':[(-60, -40), (-20, 0)],\n                      '[(-40, -20), (-20, 0)]':[(-40, -20), (-20, 0)],\n                    }\n\n\n```\n\n```\npython analysis/acc_p1p2.py\npython analysis/acc_p1p2_T2.py\npython analysis/classify.py\n```\n\n\n\n#### classify will generate a latex table\n```\ngpt4_1106 \u0026 Nostalgia *** \u0026 Nostalgia *** \u0026 Nostalgia *** \\\\\ngpt_3.5_turbo_0613 \u0026 Balanced \u0026 Nostalgia *** \u0026 Nostalgia *** \\\\\n```\n\n\n\n\n\n\u003c!-- \n\nexport PYTHONPATH=\"/mntnfs/med_data5/zhuchenghao/Freshbench_release/\"\n\n\n# extract files from ./answer_csv , and get a grey latex\ncd /mntnfs/med_data5/zhuchenghao/Freshbench_release/analysis/complex_acc_latex\npython acc_p1p2.py\n\n\ncd /mntnfs/med_data5/zhuchenghao/Freshbench_release/\npython /mntnfs/med_data5/zhuchenghao/Freshbench_release/analysis/complex_acc_latex/merge_grey.py\n\n\npython get_mean_acc_b4release.py\npython /mntnfs/med_data5/zhuchenghao/Freshbench_release/handel_latex_table.py\n\n\npython /mntnfs/med_data5/zhuchenghao/Freshbench_release/handel_latex_table.py --txt_path /mntnfs/med_data5/zhuchenghao/Freshbench_release/analysis/complex_acc_latex/latex_gray.txt \n\n\n--\u003e\n# Citation\n```\n@inproceeding{zhu2024freshbench,\n  title={Is Your LLM Outdated? A Deep Look at Temporal Generalization},\n  author={Chenghao Zhu and Nuo Chen and Yufei Gao and Yunyi Zhang and Prayag Tiwari and Benyou Wang},\n  booktitle = {Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics},\n  year={2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedomintelligence%2Ffreshbench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffreedomintelligence%2Ffreshbench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedomintelligence%2Ffreshbench/lists"}