{"id":7823,"date":"2024-12-17T15:29:45","date_gmt":"2024-12-17T15:29:45","guid":{"rendered":"https:\/\/www.aiproblog.com\/index.php\/2024\/12\/17\/facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models\/"},"modified":"2024-12-17T15:29:45","modified_gmt":"2024-12-17T15:29:45","slug":"facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models","status":"publish","type":"post","link":"https:\/\/www.aiproblog.com\/index.php\/2024\/12\/17\/facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models\/","title":{"rendered":"FACTS Grounding: A new benchmark for evaluating the factuality of large language models"},"content":{"rendered":"<p>Author: <\/p>\n<div>Our comprehensive benchmark and online leaderboard offer a much-needed measure of how accurately LLMs ground their responses in provided source material and avoid hallucinations<\/div>\n<p><a href=\"https:\/\/deepmind.google\/discover\/blog\/facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models\/\">Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Author: Our comprehensive benchmark and online leaderboard offer a much-needed measure of how accurately LLMs ground their responses in provided source material and avoid hallucinations [&hellip;] <span class=\"read-more-link\"><a class=\"read-more\" href=\"https:\/\/www.aiproblog.com\/index.php\/2024\/12\/17\/facts-grounding-a-new-benchmark-for-evaluating-the-factuality-of-large-language-models\/\">Read More<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":458,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"categories":[24],"tags":[],"_links":{"self":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/7823"}],"collection":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/comments?post=7823"}],"version-history":[{"count":0,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/7823\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media\/474"}],"wp:attachment":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media?parent=7823"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/categories?post=7823"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/tags?post=7823"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}