{"id":693980,"date":"2025-10-10T04:00:25","date_gmt":"2025-10-10T01:00:25","guid":{"rendered":"https:\/\/buradabiliyorum.com\/en\/researchers-fooled-ai-models-with-fake-dates-to-boost-visibility\/"},"modified":"2025-10-10T04:00:25","modified_gmt":"2025-10-10T01:00:25","slug":"researchers-fooled-ai-models-with-fake-dates-to-boost-visibility","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/researchers-fooled-ai-models-with-fake-dates-to-boost-visibility\/","title":{"rendered":"Researchers fooled AI models with fake dates to boost visibility"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<label for=\"ez-toc-cssicon-toggle-item-6a3bf3325a266\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #dd3333;color:#dd3333\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #dd3333;color:#dd3333\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a3bf3325a266\" checked aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/buradabiliyorum.com\/en\/researchers-fooled-ai-models-with-fake-dates-to-boost-visibility\/#Add_a_fake_2025_date_increase_your_AI_visibility_A_new_study_shows_ChatGPT_and_rivals_reward_recency_over_relevance\" >Add a fake 2025 date, increase your AI visibility. A new study shows ChatGPT and rivals reward recency over relevance.<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"subhead\" itemprop=\"alternativeHeadline\"><span class=\"ez-toc-section\" id=\"Add_a_fake_2025_date_increase_your_AI_visibility_A_new_study_shows_ChatGPT_and_rivals_reward_recency_over_relevance\"><\/span>Add a fake 2025 date, increase your AI visibility. A new study shows ChatGPT and rivals reward recency over relevance.<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><\/p>\n<div class=\"bialty-container\">\n<p>Adding fake publication dates to online content can dramatically boost its visibility across leading AI models, a team from Waseda University discovered. This seems to confirm that tools like ChatGPT systematically favor newer content over older, equally relevant material.<\/p>\n<p><strong>Why we care.<\/strong> AI models seem to reward timestamps more than quality. That means your older high-quality content could vanish from AI search results unless it\u2019s regularly updated \u2013 <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/download-scripts-themes-apps\/\" data-internallinksmanager029f6b8e52c=\"9\" title=\"Download Scripts &amp; Themes &amp; Apps\" target=\"_blank\" rel=\"noopener\">app<\/a>arently, regardless of whether those updates are substantial or artificial.<\/p>\n<p><strong>How they did it. <\/strong>Researchers added fake publication dates to passages from standardized test collections with no other changes. Then they asked seven major AI models \u2013 including GPT-4o, GPT-3.5, LLaMA-3, and Qwen-2.5 \u2013 to rank the results.<\/p>\n<p>Every model preferred the newer-dated text.<\/p>\n<ul class=\"wp-block-list\">\n<li>Top-10 results shifted 1-5 years newer on average.<\/li>\n<li>Individual passages jumped up to 95 ranking positions.<\/li>\n<li>1 in 4 relevance decisions flipped based solely on the date.<\/li>\n<\/ul>\n<p><strong>The \u201cseesaw effect.\u201d<\/strong> Across all models, top-ranked content skewed younger, while older material systematically sank:<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Ranks 1\u201310:<\/strong> 0.8\u20134.8 years fresher.<\/li>\n<li><strong>Ranks 61\u2013100:<\/strong> up to 2 years older.<\/li>\n<\/ul>\n<p>Even highly authoritative older sources \u2013 academic papers, medical research, or detailed guides \u2013 lost visibility to more recent, often less credible content<\/p>\n<p><strong>Bias.<\/strong> Here are the models that fell for it (and those that didn\u2019t): <\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Most biased:<\/strong> Meta\u2019s <strong>LLaMA-3-8B<\/strong>, which showed 25% reversal rates and nearly 5-year shifts.<\/li>\n<li><strong>Least biased:<\/strong> Alibaba\u2019s <strong>Qwen-2.5-72B<\/strong>, with only 8% reversals and minimal year shifts.<\/li>\n<li>OpenAI\u2019s <strong>GPT-4o<\/strong> and <strong>GPT-4<\/strong> fell in the middle, showing measurable but smaller recency bias.<\/li>\n<\/ul>\n<p><strong>The backstory<\/strong>. Earlier this year, independent researcher Metehan Yesilyurt found the setting <em>\u201cuse_freshness_scoring_profile: true\u201d<\/em> in ChatGPT\u2019s configuration files \u2013 evidence that OpenAI\u2019s reranking system explicitly favors recent content.<\/p>\n<p><strong>What\u2019s next<\/strong>. Yesilyurt warned of a looming \u201ctemporal arms race\u201d:<\/p>\n<ul class=\"wp-block-list\">\n<li>Publishers can boost rankings by faking \u201cUpdated for 2025\u201d labels.<\/li>\n<li>AI systems will respond by detecting superficial edits.<\/li>\n<li>Ultimately, the bias could reward receny over quality.<\/li>\n<\/ul>\n<p><strong>What they\u2019re saying.<\/strong> In response to the report, Chris Long, co-founder at Nectiv., <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/www.linkedin.com\/feed\/update\/urn:li:activity:7381667464750989312\/\" target=\"_blank\" rel=\"noopener\">wrote on LinkedIn<\/a>:<\/p>\n<ul class=\"wp-block-list\">\n<li>\u201cWhat I will say is that freshness updates are probably one of the more scalable on-page improvements you can make. For years we\u2019ve known it\u2019s helped with traditional search. Now we can see that updating content likely impacts AI visibility as well.\u201d<\/li>\n<\/ul>\n<p>Rich Tatum, fractional SEO and AI solutions architect at Edgy Labs, <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/www.linkedin.com\/feed\/update\/urn:li:activity:7381678820522659840\/\">said on LinkedIn<\/a>:<\/p>\n<ul class=\"wp-block-list\">\n<li>\u201cFreshness and recency make sense as a relevance signal for LLM models, and an archive of sources with high trust (academic papers) would logically make \u201cnaive\u201d LLMs treat such freshness signals there as highly salient and trustworthy.<\/li>\n<li>Sadly our profession will naturally abuse those signals until future LLMs have that na\u00efvet\u00e9 trained out of them. And those standard freshness signals will become mere noise.\u201d<\/li>\n<\/ul>\n<p>Which spurred <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/www.linkedin.com\/feed\/update\/urn:li:activity:7381678820522659840?commentUrn=urn%3Ali%3Acomment%3A%28activity%3A7381678820522659840%2C7381772304478822400%29&amp;dashCommentUrn=urn%3Ali%3Afsd_comment%3A%287381772304478822400%2Curn%3Ali%3Aactivity%3A7381678820522659840%29\" target=\"_blank\" rel=\"noopener\">this interesting reply<\/a> from Rand Fishkin, cofounder of SparkToro: <\/p>\n<ul class=\"wp-block-list\">\n<li>\u201cI don\u2019t think it\u2019s necessarily sad to abuse signals that llms use. I used to be very anti-spam against Google and then I saw how Google abused evil manipulative political thing in this world to gain and hold Monopoly power. The large language model AI tool providers feel no different and I see no reason why we should adopt a set of arbitrary ethics simply to acquiesce to their whims.<\/li>\n<li>What have the big tech companies and AI tool providers done that makes them deserving of respect for their systems? I cannot name a thing.\u201d<\/li>\n<\/ul>\n<p><strong>Bottom line<\/strong>. In AI search, fresh beats factual \u2013 at least for now. If your content isn\u2019t new, it\u2019s already invisible.<\/p>\n<p><strong>The report.<\/strong> <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/metehan.ai\/blog\/i-found-it-in-the-code-science-proved-it-in-the-lab-the-recency-bias-thats-reshaping-ai-search\/\">I Found It in the Code, Science Proved It in the Lab: The Recency Bias That\u2019s Reshaping AI Search<\/a> by Metehan Yesilyurt<\/p>\n<\/div>\n<blockquote><p><strong><span style=\"color: #ff6600;\">If you liked the article, do not forget to share it with your friends. Follow us on\u00a0<span style=\"color: #ff0000;\"><a style=\"color: #ff0000;\" href=\"https:\/\/news.google.com\/publications\/CAAqBwgKMN63nwsw68G3Aw\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\"><strong>If you want to read more like this article, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/buradabiliyorum.com\/en\/category\/technology\/\" target=\"_blank\" >Technology<\/a><\/span> category.<\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/searchengineland.com\/fool-ai-models-fake-dates-boost-visibility-463227\" target=\"_blank\" >Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Add a fake 2025 date, increase your AI visibility. A new study shows ChatGPT and rivals reward recency over relevance. Adding fake publication dates to online content can dramatically boost its visibility across leading AI models, a team from Waseda University discovered. This seems to confirm that tools like ChatGPT systematically favor newer content over&#8230;<\/p>\n","protected":false},"author":1,"featured_media":693981,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/searchengineland.com\/wp-content\/seloads\/2025\/10\/ai-models-2025.png","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[],"class_list":["post-693980","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/693980","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=693980"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/693980\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/693981"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=693980"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=693980"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=693980"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}