{"id":1138726,"date":"2025-05-06T13:27:59","date_gmt":"2025-05-06T20:27:59","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-video&#038;p=1138726"},"modified":"2025-12-10T10:43:05","modified_gmt":"2025-12-10T18:43:05","slug":"claimify-extracting-high-quality-claims-from-language-model-outputs","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/claimify-extracting-high-quality-claims-from-language-model-outputs\/","title":{"rendered":"Claimify: Extracting high-quality claims from language model outputs"},"content":{"rendered":"<p>Dasha Metropolitansky, Research Data Scientist, Microsoft Research Special Projects, introduces Claimify, a new method for extracting simple, verifiable claims from LLM outputs. Claim extraction is a key step in fact-checking LLM-generated content. Claimify outperforms prior techniques, ensuring that extracted claims are accurate, verifiable, and preserve critical context.<\/p>\n<p>Paper: <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/towards-effective-extraction-and-evaluation-of-factual-claims\/\" data-wplink-edit=\"true\">Towards Effective Extraction and Evaluation of Factual Claims<\/a><br \/>\nBlog post: <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/claimify-extracting-high-quality-claims-from-language-model-outputs\/\">Claimify: Extracting high-quality claims from language model outputs<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Dasha Metropolitansky, Research Data Scientist, Microsoft Research Special Projects, introduces Claimify, a new method for extracting simple, verifiable claims from LLM outputs. Claim extraction is a key step in fact-checking LLM-generated content. Claimify outperforms prior techniques, ensuring that extracted claims are accurate, verifiable, and preserve critical context. Paper: Towards Effective Extraction and Evaluation of Factual [&hellip;]<\/p>\n","protected":false},"featured_media":1138727,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_hide_image_in_river":null,"footnotes":""},"research-area":[13556,13545],"msr-video-type":[],"msr-locale":[268875],"msr-post-option":[269148,269142],"msr-session-type":[],"msr-impact-theme":[],"msr-pillar":[],"msr-episode":[],"msr-research-theme":[],"class_list":["post-1138726","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us","msr-post-option-approved-for-river","msr-post-option-include-in-river"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/WTs-Ipt0k-M","msr_secondary_video_url":"","msr_video_file":"http:\/\/0","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/1138726","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/1138726\/revisions"}],"predecessor-version":[{"id":1138730,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/1138726\/revisions\/1138730"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1138727"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1138726"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1138726"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=1138726"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1138726"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1138726"},{"taxonomy":"msr-session-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-session-type?post=1138726"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1138726"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1138726"},{"taxonomy":"msr-episode","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-episode?post=1138726"},{"taxonomy":"msr-research-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-theme?post=1138726"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}