{"id":709416,"date":"2026-01-26T21:50:16","date_gmt":"2026-01-26T18:50:16","guid":{"rendered":"https:\/\/buradabiliyorum.com\/en\/google-research-points-to-a-post-query-future-for-search-intent\/"},"modified":"2026-01-26T21:50:16","modified_gmt":"2026-01-26T18:50:16","slug":"google-research-points-to-a-post-query-future-for-search-intent","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/google-research-points-to-a-post-query-future-for-search-intent\/","title":{"rendered":"Google research points to a post-query future for search intent"},"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-6a41d7bfd8cd3\" 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-6a41d7bfd8cd3\" 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\/google-research-points-to-a-post-query-future-for-search-intent\/#Google_signals_searchs_next_phase_small_multimodal_models_on_devices_infer_intent_from_behavior_before_a_query_is_ever_typed\" >Google signals search\u2019s next phase: small multimodal models on devices infer intent from behavior before a query is ever typed.<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"subhead\" itemprop=\"alternativeHeadline\"><span class=\"ez-toc-section\" id=\"Google_signals_searchs_next_phase_small_multimodal_models_on_devices_infer_intent_from_behavior_before_a_query_is_ever_typed\"><\/span>Google signals search\u2019s next phase: small multimodal models on devices infer intent from behavior before a query is ever typed.<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><\/p>\n<div class=\"bialty-container\">\n<p>Google is working toward a future where it understands what you want before you ever type a search.<\/p>\n<p>Now Google is pushing that thinking onto the device itself, using small AI models that perform nearly as well as much larger ones.<\/p>\n<p><strong>What\u2019s h<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>ening.<\/strong> In a research paper presented at EMNLP 2025, Google researchers show that a simple shift makes this possible: break \u201cintent understanding\u201d into smaller steps. When they do, small\u00a0multimodal LLMs (MLLMs) become powerful enough to match systems like Gemini 1.5 Pro \u2014 while running faster, costing less, and keeping data on the device.<\/p>\n<ul class=\"wp-block-list\">\n<li>The paper, \u201c<a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/aclanthology.org\/2025.emnlp-main.949\/\" target=\"_blank\" rel=\"noopener\">Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition<\/a>,\u201d explains how Google infers what someone is trying to do based on how they use apps and websites. That includes taps, clicks, scrolling, and screen changes over time.<\/li>\n<\/ul>\n<p><strong>The future is intent extraction.<\/strong> Large AI models can already infer intent from user behavior, but they usually run in the cloud. That creates three problems. They\u2019re slower. They\u2019re more expensive. And they raise privacy concerns, because user actions can be sensitive.<\/p>\n<p>Google\u2019s solution is to split the task into two simple steps that small, on-device models can handle well.<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Step one:<\/strong> Each screen interaction is summarized separately. The system records what was on the screen, what the user did, and a tentative guess about why they did it.<\/li>\n<li><strong>Step two:<\/strong> Another small model reviews only the factual parts of those summaries. It ignores the guesses and produces one short statement that explains the user\u2019s overall goal for the session.\n<ul class=\"wp-block-list\">\n<li>By keeping each step focused, the system avoids a common failure mode of small models: breaking down when asked to reason over long, messy histories all at once.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><strong>How the researchers measure success.<\/strong> Instead of asking whether an intent summary \u201clooks similar\u201d to the right answer, they use a method called Bi-Fact. Using its main quality metric, an F1 score, small models with the step-by-step approach consistently outperform other small-model methods:<\/p>\n<ul class=\"wp-block-list\">\n<li>Gemini 1.5 Flash, an 8B model, matches the performance of Gemini 1.5 Pro on mobile behavior data. <\/li>\n<li>Hallucinations drop because speculative guesses are s<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/trip-and-travel\/\" data-internallinksmanager029f6b8e52c=\"10\" title=\"Trip &amp; Travel\" target=\"_blank\" rel=\"noopener\">trip<\/a>ped out before the final intent is written. <\/li>\n<li>Even with extra steps, the system runs faster and cheaper than cloud-based large models.<\/li>\n<\/ul>\n<p><strong>How it works.<\/strong> Intent is broken into small pieces of information, or facts. Then they measure which facts are missing and which ones were invented. This:<\/p>\n<ul class=\"wp-block-list\">\n<li>Shows <strong>how<\/strong> intent understanding fails, not just that it fails. <\/li>\n<li>Reveals where systems tend to hallucinate meaning versus where they drop important details.<\/li>\n<\/ul>\n<p>The paper also shows that messy training data hurts large, end-to-end models more than it hurts this step-by-step approach. When labels are noisy \u2014 which is common with real user behavior \u2014 the decomposed system holds up better.<\/p>\n<p><strong>Why we care.<\/strong> If Google wants agents that suggest actions or answers before people search, it needs to understand intent from user behavior (how people move through apps, browsers, and screens). This research moves this idea closer to reality. Keywords will still matter, but the query will be just one signal. In this future, you\u2019ll have to optimize for clear, logical user journeys \u2014 not just the words typed at the end.<\/p>\n<p><strong>The Google Research blog post.<\/strong> <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/research.google\/blog\/small-models-big-results-achieving-superior-intent-extraction-through-decomposition\/\" target=\"_blank\" rel=\"noopener\">Small models, big results: Achieving superior intent extraction through decomposition<\/a><\/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\/google-research-small-models-intent-extraction-467960\" target=\"_blank\" >Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google signals search\u2019s next phase: small multimodal models on devices infer intent from behavior before a query is ever typed. Google is working toward a future where it understands what you want before you ever type a search. Now Google is pushing that thinking onto the device itself, using small AI models that perform nearly&#8230;<\/p>\n","protected":false},"author":1,"featured_media":709417,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/searchengineland.com\/wp-content\/seloads\/2026\/01\/google-intent-extraction.png","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[],"class_list":["post-709416","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\/709416","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=709416"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/709416\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/709417"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=709416"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=709416"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=709416"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}