{"id":1772,"date":"2025-06-11T13:36:08","date_gmt":"2025-06-11T17:36:08","guid":{"rendered":"https:\/\/ozer.gt\/log\/?p=1772"},"modified":"2025-06-11T14:37:43","modified_gmt":"2025-06-11T18:37:43","slug":"using-llms-for-iv-discovery-and-data","status":"publish","type":"post","link":"https:\/\/ozer.gt\/log\/2025\/06\/11\/using-llms-for-iv-discovery-and-data\/","title":{"rendered":"Using LLMs for IV discovery and data"},"content":{"rendered":"

LLMs excel at search and discovery. Why not use them to find IVs for causal models?<\/p>\n

In a new section in Causal Book, Using LLMs for IV discovery and data<\/a><\/strong>, we offer a prompt template to help discover candidate IVs and their actual data. We tested it with the latest Gemini (2.5 Pro Preview 06-05-2025) and the results are promising.<\/p>\n

This section is the latest addition to the IV design pattern chapter of Causal Book. The book itself aims to:<\/p>\n

    \n
  1. provide solution patterns and their code implementations in R and Python,<\/li>\n
  2. discuss different approaches to the same pattern on the same data (Statistics, Machine Learning, Bayesian),<\/li>\n
  3. demystify some surprising (or seemingly surprising) challenges in applying the causal design patterns.<\/li>\n<\/ol>\n

    See the full table of contents here<\/a>.<\/p>\n

    We’ll next dive into the regression discontinuity design pattern, which I hope will be even more fun with the newly added support in DoubleML.<\/p>\n","protected":false},"excerpt":{"rendered":"

    LLMs excel at search and discovery. Why not use them to find IVs for causal models? In a new section in Causal Book, Using LLMs for IV discovery and data, we offer a prompt template to help discover candidate IVs and their actual data. We tested it with the latest Gemini (2.5 Pro Preview 06-05-2025) […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"cybocfi_hide_featured_image":"","footnotes":""},"categories":[1],"tags":[],"class_list":["post-1772","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/posts\/1772","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/comments?post=1772"}],"version-history":[{"count":16,"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/posts\/1772\/revisions"}],"predecessor-version":[{"id":1788,"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/posts\/1772\/revisions\/1788"}],"wp:attachment":[{"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/media?parent=1772"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/categories?post=1772"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ozer.gt\/log\/wp-json\/wp\/v2\/tags?post=1772"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}