{"id":16593,"date":"2024-09-20T12:27:20","date_gmt":"2024-09-20T10:27:20","guid":{"rendered":"https:\/\/is.ijs.si\/?p=16593"},"modified":"2025-03-26T13:19:29","modified_gmt":"2025-03-26T12:19:29","slug":"fact-manipulation-in-news-llm-driven-synthesis-and-evaluation-of-fake-news-annotation","status":"publish","type":"post","link":"https:\/\/is.ijs.si\/?p=16593","title":{"rendered":"Fact Manipulation in News: LLM-Driven Synthesis and Evaluation of Fake News Annotation"},"content":{"rendered":"\n<p>Luka Golob and Abdul Sittar<\/p>\n<p><strong>Abstract<\/strong><br \/>Advancements in artificial intelligence and increased internet<br \/>accessibility have made it simpler to create and disseminate fake<br \/>news with customized content. However, they also improved the<br \/>ability to analyze and identify such misinformation. To effectively<br \/>train high-performance models, we require high-quality, up-to-<br \/>date training datasets. This article delves into the potential for<br \/>generating fake news through factual modifications of articles.<br \/>This is facilitated by prompt-based content generated by large<br \/>language models (LLMs), which can identify and manipulate<br \/>facts. We intend to outline our methodology, highlighting both<br \/>the capabilities and limitations of this approach. Additionally,<br \/>this effort has resulted in new quality synthetic data that can be<br \/>incorporated into the standard FAK-ES dataset.<\/p>\n<p>\u00a0<\/p>\n\n\n\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/is.ijs.si\/wp-content\/uploads\/2024\/10\/IS2024_-_SIKDD_2024_paper_13-1.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of IS2024_-_SIKDD_2024_paper_13-1.\"><\/object><a id=\"wp-block-file--media-358b4f4e-7f7e-446d-8c81-7f361301d73e\" href=\"https:\/\/is.ijs.si\/wp-content\/uploads\/2024\/10\/IS2024_-_SIKDD_2024_paper_13-1.pdf\">IS2024_-_SIKDD_2024_paper_13-1<\/a><a href=\"https:\/\/is.ijs.si\/wp-content\/uploads\/2024\/10\/IS2024_-_SIKDD_2024_paper_13-1.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-358b4f4e-7f7e-446d-8c81-7f361301d73e\">Download<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":29,"featured_media":24966,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[109,102],"tags":[],"class_list":["post-16593","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-doi-sikdd-2024","category-papers"],"_links":{"self":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts\/16593","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/users\/29"}],"replies":[{"embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=16593"}],"version-history":[{"count":3,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts\/16593\/revisions"}],"predecessor-version":[{"id":25005,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts\/16593\/revisions\/25005"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/media\/24966"}],"wp:attachment":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16593"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=16593"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=16593"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}