{"id":6669498,"date":"2026-01-04T08:00:00","date_gmt":"2026-01-04T13:00:00","guid":{"rendered":"https:\/\/www.learningandthebrain.com\/blog\/?p=6669498"},"modified":"2025-12-31T08:20:01","modified_gmt":"2025-12-31T13:20:01","slug":"answering-questions-before-reading-can-ai-make-this-strategy-work","status":"publish","type":"post","link":"https:\/\/www.learningandthebrain.com\/blog\/answering-questions-before-reading-can-ai-make-this-strategy-work\/","title":{"rendered":"Answering Questions *Before* Reading: Can AI Make This Strategy Work?"},"content":{"rendered":"\n<p>2025 included MANY grand claims about transformational potential for AI:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>&#8220;AI will enhance education (and civilization) in <em>these magnificent ways<\/em>,&#8221; or<\/li>\n\n\n\n<li>&#8220;AI will destroy education (and civilization) in <em>these grisly ways<\/em>.&#8221;<\/li>\n<\/ul>\n\n\n\n<p>Here&#8217;s a question that got less air time: <\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>&#8220;Can you name me just one specific &#8212; even mundane &#8212; way that AI can make teaching and learning simpler and better?&#8221;<\/p>\n<\/blockquote>\n\n\n\n<p>As of today, my answer to <em>that <\/em>question is YES.<\/p>\n\n\n\n<p>Here&#8217;s the story.<\/p>\n\n\n\n<p>Regular readers have heard me talk about the benefits of &#8220;prequestions&#8221; before: for example, <a href=\"https:\/\/www.learningandthebrain.com\/blog\/getting-the-details-just-right-pre-questions\/\" data-type=\"post\" data-id=\"7244\">here<\/a>, <a href=\"https:\/\/www.learningandthebrain.com\/blog\/starting-class-with-prequestions-benefits-problems-solutions\/\" data-type=\"post\" data-id=\"6952\">here<\/a>, and <a href=\"https:\/\/www.learningandthebrain.com\/blog\/how-to-reduce-mind-wandering-during-class\/\" data-type=\"post\" data-id=\"3205407\">here<\/a>.<\/p>\n\n\n\n<p>The prequestion process goes like this:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Students try to answer questions about a topic <em>even though they haven&#8217;t learned about it yet<\/em>.<\/li>\n\n\n\n<li>Unsurprisingly, they answer most of these questions incorrectly. <\/li>\n\n\n\n<li>Students then read a passage on the topic.<\/li>\n\n\n\n<li>Result: these students <em>remember more about the topic <\/em>than others who didn&#8217;t answer prequestions.<\/li>\n<\/ul>\n\n\n\n<p>By the way: these prequestions can be very straightforward. For instance: &#8220;What distinguishes hydraulic brakes from mechanical brakes in automobiles?&#8221;<\/p>\n\n\n\n<p>Researchers are still trying to figure out WHY prequestions help learning; they&#8217;ve got several theories. But we&#8217;ve got enough research on this strategy for me to conclude that it&#8217;s a thing &#8212; not a well-intentioned research-based fluke.<\/p>\n\n\n\n<p>As we try to apply this finding in actual classrooms, we come across a few stark problems:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>For teachers: writing prequestions takes time. (Boo!)<\/li>\n\n\n\n<li>For students: how can they write their own prequestions when they haven&#8217;t studied the material? (Paradox!)<\/li>\n<\/ul>\n\n\n\n<p>A research team &#8212; led by Dr. Steven Pan &#8212; <a href=\"https:\/\/psycnet.apa.org\/record\/2026-78173-001\">wondered<\/a>: <em>can we use AI to generate effective prequestions<\/em>? That is: do AI-created prequestions benefit learning the same way that human-generated prequestions do?<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Researching Step by Step<\/h2>\n\n\n\n<p>Team Pan&#8217;s questions sound simple. But when researchers approach a topic like this, they face several demands. <\/p>\n\n\n\n<p>First: they have lots technical steps to follow: sample sizes and active control groups and intricate calculations and so forth. (In my estimation, they checked all these boxes.)<\/p>\n\n\n\n<p>Second: when done well, research studies try to <strong>disprove<\/strong> their own hypotheses. Researchers don&#8217;t so much <em>kick <\/em>the tires as <em>try to puncture them<\/em>. (In my view, they explored plausible alternatives admirably.)<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1024\" height=\"439\" src=\"https:\/\/www.learningandthebrain.com\/blog\/wp-content\/uploads\/2026\/01\/AdobeStock_1595580543-1024x439.jpeg\" alt=\"\" class=\"wp-image-6669558\" srcset=\"https:\/\/www.learningandthebrain.com\/blog\/wp-content\/uploads\/2026\/01\/AdobeStock_1595580543-1024x439.jpeg 1024w, https:\/\/www.learningandthebrain.com\/blog\/wp-content\/uploads\/2026\/01\/AdobeStock_1595580543-300x129.jpeg 300w, https:\/\/www.learningandthebrain.com\/blog\/wp-content\/uploads\/2026\/01\/AdobeStock_1595580543-768x329.jpeg 768w, https:\/\/www.learningandthebrain.com\/blog\/wp-content\/uploads\/2026\/01\/AdobeStock_1595580543-1536x658.jpeg 1536w, https:\/\/www.learningandthebrain.com\/blog\/wp-content\/uploads\/2026\/01\/AdobeStock_1595580543-2048x878.jpeg 2048w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>To meet these challenges, Pan&#8217;s crew undertook four related experiments. I won&#8217;t go through all the nitty gritty, but the highlights make for encouraging reading.<\/p>\n\n\n\n<p>In Pan&#8217;s most basic experiment, one group of students read a passage about different kinds of brakes: air brakes, mechanical brakes, hydraulic brakes &#8212; you get the idea. A second group read two AI-generated prequestions about that passage before they read it. Sure enough: the students who read the AI-created prequestions scored higher on a follow-up quiz than those who didn&#8217;t.<\/p>\n\n\n\n<p>Unsurprisingly, they scored higher when answering the same questions that they initially read as prequestions. They ALSO scored higher when answering novel questions. In other words: it seems that the benefits of answering prequestions goes beyond the precise questions themselves to the passage overall.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Don&#8217;t Stop Now<\/h2>\n\n\n\n<p>To make sure they have a persuasive case, Pan&#8217;s team didn&#8217;t stop there. <\/p>\n\n\n\n<p>They asked: <em>do AI-generated prequestions provide as much benefit as human-generated prequestions<\/em>?<\/p>\n\n\n\n<p>Short answer: &#8220;yes.&#8221; Technically speaking, in some cases the human-generated prequestions led to slightly higher quiz scores &#8212; but the differences were tiny.<\/p>\n\n\n\n<p>They asked: <em>do AI-generated prequestions help more or less than previewing an AI-generated outline?<\/em><\/p>\n\n\n\n<p>Short answer: &#8220;trying to answer the prequestions helped considerably more than previewing an outline.&#8221;<\/p>\n\n\n\n<p>They asked: <em>do detailed prompts produce better questions, or does a basic prompt work well too?<\/em><\/p>\n\n\n\n<p>Short answer: &#8220;a basic prompt worked just fine.&#8221; In one study, the basic prompt led to more effective prequestions than the detailed one.<\/p>\n\n\n\n<p>To summarize the good news in this study:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>AI-generated prequestions help students learn from reading new information<\/li>\n\n\n\n<li>They help as much as human-generated prequestions<\/li>\n\n\n\n<li>Prequestions improve memory of the entire passage &#8212; not just the answers to the questions themselves<\/li>\n\n\n\n<li>They help more than some other kinds of warm-up activities, like studying an outline<\/li>\n\n\n\n<li>Even basic prompts work just fine<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Good News&#8230;Bad News?<\/h2>\n\n\n\n<p>With all that good news, is there any bad news?<\/p>\n\n\n\n<p>Honestly, I don&#8217;t see much &#8220;bad news&#8221; here. But &#8212; as always &#8212; I do see <em>limitations<\/em>.<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>As far as I know, prequestions have been studied for learning from reading passages. I don&#8217;t know if we have evidence showing they benefit students who, say, listen to a discussion or a teacher presentation. For that reason, this strategy isn&#8217;t obviously road-tested for younger grades.<\/li>\n\n\n\n<li>This study focused on adult learners; the average participant age for these studies was in the low 30s. We don&#8217;t know if AI-generated prequestions will help in 8th grade &#8212; although it&#8217;s not obvious to me why they wouldn&#8217;t.<\/li>\n\n\n\n<li>This study, like most research into prequestions, tests memory after a few minutes. Will it help over longer periods of time? I don&#8217;t think we know.<\/li>\n\n\n\n<li>Prequestions aren&#8217;t a panacea. We don&#8217;t need to use them all the time. They should be one strategy that we use judiciously, not a hard-and-fast requirement.<\/li>\n<\/ol>\n\n\n\n<p>Once we acknowledge those limitations, I think we have a compelling case. We know that &#8212; under the right circumstances &#8212; prequestions can help students learn. And, thanks to Pan and his colleagues, we know that AI-generated prequestions provide the benefits we want.<\/p>\n\n\n\n<p>At the top of this post, I asked this question: &#8220;Can you name me just one specific &#8212; even mundane &#8212; way that AI can make teaching and learning simpler and better?&#8221; <\/p>\n\n\n\n<p>Team Pan answers: &#8220;AI can help both students and teachers generate prequestions. And those AI-created questions help learning.&#8221;<\/p>\n\n\n\n<p>Perhaps you&#8217;ll begin new classroom year with a prequestion or two.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\"\/>\n\n\n\n<p>Pan, S. C., Schweppe, J., Teo, A. Z. J., Indrajaya, A., &amp; Wenzel, N. (2025). Using ChatGPT-generated prequestions to improve memory and text comprehension. Journal of Applied Research in Memory and Cognition. Advance online publication. https:\/\/dx.doi.org\/10.1037\/mac0000254<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>2025 included MANY grand claims about transformational potential for AI: Here&#8217;s a question that got less air time: &#8220;Can you name me just one specific &#8212; even mundane &#8212; way that AI can make teaching and learning simpler and better?&#8221; As of today, my answer to that question is YES. Here&#8217;s the story. Regular readers [&hellip;]<\/p>\n","protected":false},"author":18,"featured_media":6669558,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[250,203],"class_list":["post-6669498","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-lb-blog","tag-ai","tag-prequestions"],"_links":{"self":[{"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/posts\/6669498","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/users\/18"}],"replies":[{"embeddable":true,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/comments?post=6669498"}],"version-history":[{"count":12,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/posts\/6669498\/revisions"}],"predecessor-version":[{"id":6669606,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/posts\/6669498\/revisions\/6669606"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/media\/6669558"}],"wp:attachment":[{"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/media?parent=6669498"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/categories?post=6669498"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.learningandthebrain.com\/blog\/wp-json\/wp\/v2\/tags?post=6669498"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}