{"id":21120402,"url":"https://github.com/TIGER-AI-Lab/TableCoT","last_synced_at":"2025-07-08T20:31:35.744Z","repository":{"id":80083667,"uuid":"555961600","full_name":"TIGER-AI-Lab/TableCoT","owner":"TIGER-AI-Lab","description":"The code and data for paper \"Large Language Models are few(1)-shot Table Reasoners\" [EACL2023]","archived":false,"fork":false,"pushed_at":"2024-04-30T15:30:52.000Z","size":4283,"stargazers_count":46,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-04T10:26:19.275Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/TIGER-AI-Lab.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":"2022-10-22T18:44:27.000Z","updated_at":"2025-03-06T13:44:53.000Z","dependencies_parsed_at":null,"dependency_job_id":"e488ddbb-8ad5-4b51-887d-ca642de266d8","html_url":"https://github.com/TIGER-AI-Lab/TableCoT","commit_stats":null,"previous_names":["tiger-ai-lab/tablecot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TIGER-AI-Lab/TableCoT","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FTableCoT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FTableCoT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FTableCoT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FTableCoT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TIGER-AI-Lab","download_url":"https://codeload.github.com/TIGER-AI-Lab/TableCoT/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FTableCoT/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264343605,"owners_count":23593757,"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":[],"created_at":"2024-11-20T03:09:32.827Z","updated_at":"2025-07-08T20:31:34.286Z","avatar_url":"https://github.com/TIGER-AI-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TableCoT\nThe code and data used for EACL-2023 Paper [Large Language Models are few(1)-shot Table Reasoners](https://arxiv.org/abs/2210.06710)\n\n\n## Preliminary\nFirst, you need to specify your OPENAI_API_KEY, please find it in your account in https://openai.com/api/.\n```\nexport OPENAI_KEY=[YOUR_KEY]\n```\n\n## For WikiTableQuestions\n```\npython prompt.py --start 0 --end 500\n```\nThis will call Chain of Thoughts prompting to solve the 0-500 example in the test set of WikiTableQA. The output will be saved to output/response_..._s0_e500.json.\n\nYou can further call this following to extract the answers from the predictions.\n```\ncd outputs/\npython postprocess_answer.py --inputs response_..._s0_e500.json\n```\n\nFinally, call this following to compute the final EM score.\n```\npython compute_scores.py --inputs response_..._s0_e500.json.processed\n```\n\n## For TabFact\n```\npython prompt.py --start 0 --end 500\n```\nThis will call Chain of Thoughts prompting to solve the 0-500 example in the test set of WikiTableQA. The output will be saved to output/response_..._s0_e500.json. This will directly output the accuracy after it finishes.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTIGER-AI-Lab%2FTableCoT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTIGER-AI-Lab%2FTableCoT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTIGER-AI-Lab%2FTableCoT/lists"}