{
 "@context": "https://schema.org",
 "@type": "ScholarlyArticle",
 "@id": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#paper",
 "aboutThisFile": {
  "whatThisIs": "A research brief: a structured summary of one paper, prepared for seanrintel.com from the paper's full text.",
  "howItWasMade": "This brief was prepared with AI assistance and published by Sean Rintel. It is not the authors' published text.",
  "whatIsVerbatim": "Only 'quote' fields, figure captions and 'abstract' are the authors' own words. Research questions follow the paper's wording where it states them. Takeaway, summaries, answers, definitions and method are the site's plain-language paraphrase.",
  "howItIsChecked": "Before publication every quote is matched against the paper and every number in the brief is found in it. 'verified' is the date of the last check.",
  "howToUse": [
   "For a quick answer, use 'takeaway' and 'questions'. For evidence, use 'findings' (each has a verbatim quote, its location in the paper and a 'url' anchored to that finding on the paper's page).",
   "Locations such as '§5.2, p. 9' refer to the version at 'pageNumbersReferTo'.",
   "For anything not covered here, read the paper itself: 'fullTextSources' lists free versions first.",
   "If 'researchOverview' is present, the paper is part of one of Sean Rintel's research overviews: it gives the overview's thesis, the claims this paper is evidence for and its role in each, and the other papers in the overview.",
   "To find other papers by Sean Rintel, use the catalogue at https://seanrintel.com/publications/index.json."
  ],
  "authorship": "Sean Rintel's role on each paper: lead author when he is first author, sole author when he is the only author, and otherwise senior author. Senior author here means the senior researcher on the team, whatever his position in the author list.",
  "howToCite": "Cite the paper, not this file: use 'citation' or the ready-made 'bibtex' (DOI where given) and name every author. Attribute paraphrase to the paper's findings, and use quotation marks only for 'quote' text."
 },
 "name": "Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools",
 "author": [
  {
   "@type": "Person",
   "name": "Pia Kreijkes"
  },
  {
   "@type": "Person",
   "name": "Viktor Kewenig"
  },
  {
   "@type": "Person",
   "name": "Martina Kuvalja"
  },
  {
   "@type": "Person",
   "name": "Mina Lee"
  },
  {
   "@type": "Person",
   "name": "Jake Hofman"
  },
  {
   "@type": "Person",
   "name": "Sylvia Vitello"
  },
  {
   "@type": "Person",
   "name": "Abigail Sellen"
  },
  {
   "@type": "Person",
   "@id": "https://seanrintel.com/#sean-rintel",
   "name": "Sean Rintel",
   "url": "https://seanrintel.com/",
   "sameAs": [
    "https://orcid.org/0000-0003-0840-0546",
    "https://scholar.google.com/citations?user=xc25GRgAAAAJ",
    "https://www.wikidata.org/wiki/Q102369654",
    "https://www.microsoft.com/en-us/research/people/serintel/",
    "https://www.linkedin.com/in/seanrintel"
   ]
  },
  {
   "@type": "Person",
   "name": "Daniel G. Goldstein"
  },
  {
   "@type": "Person",
   "name": "David Rothschild"
  },
  {
   "@type": "Person",
   "name": "Lev Tankelevitch"
  },
  {
   "@type": "Person",
   "name": "Tim Oates"
  }
 ],
 "datePublished": "2025-11",
 "doi": "10.1016/j.compedu.2025.105514",
 "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html",
 "citation": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514",
 "bibtex": "@article{kreijkes2025effects,\nauthor = {Kreijkes, Pia and Kewenig, Viktor and Kuvalja, Martina and Lee, Mina and Hofman, Jake and Vitello, Sylvia and Sellen, Abigail and Rintel, Sean and Goldstein, Daniel G. and Rothschild, David and Tankelevitch, Lev and Oates, Tim},\ntitle = {Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools},\nyear = {2025},\nmonth = {November},\nurl = {https://doi.org/10.1016/j.compedu.2025.105514},\njournal = {Computers & Education},\ndoi = {10.1016/j.compedu.2025.105514},\n}",
 "abstract": "Students’ rapid uptake of Generative Artificial Intelligence tools, particularly large language models (LLMs), raises urgent questions about their effects on learning. We compared the impact of LLM use to that of traditional note-taking, or a combination of both, on secondary school students’ reading comprehension and retention. We conducted a pre-registered, randomised controlled experiment with within- and between-participant design elements in schools in England. 405 students, aged 14-15 years, studied two text passages and completed comprehension and retention tests three days later. Quantitative results demonstrated that both note-taking alone and combined with LLM use had significant positive effects on retention and comprehension compared to using the LLM alone. Yet, most students preferred using the LLM over note-taking, and perceived it as more helpful. Qualitative results revealed that many students valued the LLM for making complex material more accessible and reducing cognitive load, while they appreciated note-taking for promoting deeper engagement and aiding memory. Additionally, we identified “archetypes” of prompting behaviour, offering insights into the different ways students interacted with the LLM. Overall, our findings suggest that, while note-taking promotes cognitive engagement and long-term comprehension and retention, LLMs may facilitate initial understanding and student interest. The study reveals the continued importance of traditional learning activities, the benefits of combining LLM use with traditional learning over using LLMs alone, and the AI skills that students need to maximise those benefits.",
 "fullTextSources": [
  {
   "kind": "freeAccess",
   "url": "https://doi.org/10.1016/j.compedu.2025.105514",
   "label": "DOI (Free Access)"
  },
  {
   "kind": "freeAccess",
   "url": "https://www.sciencedirect.com/science/article/pii/S0360131525002829?dgcid=author",
   "label": "Publication"
  }
 ],
 "fullTextAvailable": true,
 "takeaway": "Secondary-school students learning from history texts understood and remembered more three days later when they took notes, alone or alongside an AI chatbot, than when using the chatbot alone. The chatbot possibly did the summarising work for them, yet students enjoyed it more and found it easier.",
 "researchOverview": {
  "name": "Better Thinking With AI",
  "page": "https://seanrintel.com/better-thinking-with-ai.html",
  "json": "https://seanrintel.com/overviews/better-thinking-with-ai.json",
  "markdown": "https://seanrintel.com/overviews/better-thinking-with-ai.md",
  "thesis": "Generative AI moves people's thinking into stating what they want and judging what they get. The easiest way to use it can help least, so good tools ask people to think first.",
  "claimsThisPaperFeeds": [
   {
    "claim": "What feels helpful is not always what helps",
    "role": "core evidence",
    "url": "https://seanrintel.com/better-thinking-with-ai.html#a4"
   },
   {
    "claim": "How people use AI shapes what they learn, and that skill is unevenly spread",
    "role": "core evidence",
    "url": "https://seanrintel.com/better-thinking-with-ai.html#a5"
   }
  ],
  "otherPapers": [
   {
    "study": "Review: productivity loss with AI",
    "title": "Ironies of Generative AI: Understanding and Mitigating Productivity Loss in Human-AI Interaction",
    "page": "https://seanrintel.com/publications/ironies-of-generative-ai-understanding-and-mitigating-productivity-loss-in-human-ai-interaction.html",
    "researchBrief": "https://seanrintel.com/publications/ironies-of-generative-ai-understanding-and-mitigating-productivity-loss-in-human-ai-interaction.json"
   },
   {
    "study": "Survey: critical thinking at work",
    "title": "The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge Workers",
    "page": "https://seanrintel.com/publications/the-impact-of-generative-ai-on-critical-thinking-self-reported-reductions-in-cognitive-effort-and-confidence-effects-from-a-survey-of-knowledge-workers.html",
    "researchBrief": "https://seanrintel.com/publications/the-impact-of-generative-ai-on-critical-thinking-self-reported-reductions-in-cognitive-effort-and-confidence-effects-from-a-survey-of-knowledge-workers.json"
   },
   {
    "study": "Position paper: what skill at work means",
    "title": "The Future of Skill: What Is It to Be Skilled at Work?",
    "page": "https://seanrintel.com/publications/the-future-of-skill-what-is-it-to-be-skilled-at-work.html",
    "researchBrief": "https://seanrintel.com/publications/the-future-of-skill-what-is-it-to-be-skilled-at-work.json"
   },
   {
    "study": "Conceptual analysis: metacognition and AI",
    "title": "The Metacognitive Demands and Opportunities of Generative AI",
    "page": "https://seanrintel.com/publications/the-metacognitive-demands-and-opportunities-of-generative-ai.html",
    "researchBrief": "https://seanrintel.com/publications/the-metacognitive-demands-and-opportunities-of-generative-ai.json"
   },
   {
    "study": "Prompting study: AI-assisted data analysis",
    "title": "“It’s like a rubber duck that talks back”: Understanding Generative AI-Assisted Data Analysis Workflows through a Participatory Prompting Study",
    "page": "https://seanrintel.com/publications/its-like-a-rubber-duck-that-talks-back-understanding-generative-ai-assisted-data-analysis-workflows-through-a-participatory-prompting-study.html",
    "researchBrief": "https://seanrintel.com/publications/its-like-a-rubber-duck-that-talks-back-understanding-generative-ai-assisted-data-analysis-workflows-through-a-participatory-prompting-study.json"
   },
   {
    "study": "Method paper: participatory prompting",
    "title": "Participatory prompting: a user-centric research method for eliciting AI assistance opportunities in knowledge workflows",
    "page": "https://seanrintel.com/publications/participatory-prompting-a-user-centric-research-method-for-eliciting-ai-assistance-opportunities-in-knowledge-workflows.html",
    "researchBrief": "https://seanrintel.com/publications/participatory-prompting-a-user-centric-research-method-for-eliciting-ai-assistance-opportunities-in-knowledge-workflows.json"
   },
   {
    "study": "Commentary: role-based prompts",
    "title": "Productivity implications for generative AI role-based prompts as a networked hermeneutic (Commentary)",
    "page": "https://seanrintel.com/publications/productivity-implications-for-generative-ai-role-based-prompts-as-a-networked-hermeneutic.html",
    "researchBrief": "https://seanrintel.com/publications/productivity-implications-for-generative-ai-role-based-prompts-as-a-networked-hermeneutic.json"
   },
   {
    "study": "Randomised trial: how students learn with AI",
    "title": "Learning behavior accounts for background-related advantage in AI-assisted education",
    "page": "https://seanrintel.com/publications/learning-behavior-accounts-for-background-related-advantage-in-ai-assisted-education.html",
    "researchBrief": "https://seanrintel.com/publications/learning-behavior-accounts-for-background-related-advantage-in-ai-assisted-education.json"
   },
   {
    "study": "Interviews: AI in higher education",
    "title": "The New Calculator? Practices, Norms, and Implications of Generative AI in Higher Education",
    "page": "https://seanrintel.com/publications/the-new-calculator-practices-norms-and-implications-of-generative-ai-in-higher-education.html",
    "researchBrief": "https://seanrintel.com/publications/the-new-calculator-practices-norms-and-implications-of-generative-ai-in-higher-education.json"
   },
   {
    "study": "Randomised experiment: scaffolds for AI-assisted writing",
    "title": "Metacognitive Scaffolds Create Productive Friction for AI-Assisted Knowledge Work",
    "page": "https://seanrintel.com/publications/metacognitive-scaffolds-create-productive-friction-for-ai-assisted-knowledge-work.html",
    "researchBrief": "https://seanrintel.com/publications/metacognitive-scaffolds-create-productive-friction-for-ai-assisted-knowledge-work.json"
   },
   {
    "study": "Lab study: prompt refinement controls",
    "title": "Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks",
    "page": "https://seanrintel.com/publications/dynamic-prompt-middleware-contextual-prompt-refinement-controls-for-comprehension-tasks.html",
    "researchBrief": "https://seanrintel.com/publications/dynamic-prompt-middleware-contextual-prompt-refinement-controls-for-comprehension-tasks.json"
   },
   {
    "study": "Workshop proposal: AI as a tool for thought",
    "title": "Tools for Thought: Understanding, Protecting, and Augmenting Human Cognition with Generative AI — From Vision to Implementation",
    "page": "https://seanrintel.com/publications/tools-for-thought-understanding-protecting-and-augmenting-human-cognition-with-generative-ai-from-vision-to-implementation.html",
    "researchBrief": "https://seanrintel.com/publications/tools-for-thought-understanding-protecting-and-augmenting-human-cognition-with-generative-ai-from-vision-to-implementation.json"
   },
   {
    "study": "System design: AI agents for diverse ideas",
    "title": "YES AND: A Generative AI Multi-Agent Framework for Enhancing Diversity of Thought in Individual Ideation for Problem-Solving Through Confidence-Based Agent Turn-Taking",
    "page": "https://seanrintel.com/publications/yes-and-a-generative-ai-multi-agent-framework-for-enhancing-diversity-of-thought-in-individual-ideation-for-problem-solving-through-confidence-based-agent-turn-taking.html",
    "researchBrief": "https://seanrintel.com/publications/yes-and-a-generative-ai-multi-agent-framework-for-enhancing-diversity-of-thought-in-individual-ideation-for-problem-solving-through-confidence-based-agent-turn-taking.json"
   },
   {
    "study": "Interviews and experiment: how people and machines interpret",
    "title": "Meeting in the Middle: The Interpretation Gap Between People and Machines",
    "page": "https://seanrintel.com/publications/meeting-in-the-middle-the-interpretation-gap-between-people-and-machines.html",
    "researchBrief": "https://seanrintel.com/publications/meeting-in-the-middle-the-interpretation-gap-between-people-and-machines.json"
   }
  ]
 },
 "whyItMatters": {
  "stateOfTheArt": {
   "summary": "Studies of LLMs in education mostly measure task performance, sometimes with the LLM available during assessment, and mostly in higher education, so little is known about effects on genuine learning.",
   "quote": "Consequently, there are substantial gaps in our understanding of how the use of LLMs affects genuine learning.",
   "location": "§1, pp. 1–2"
  },
  "contribution": {
   "summary": "A large, pre-registered randomised experiment in secondary schools comparing LLM use with note-taking and with both combined, measuring comprehension and retention days later, plus engagement and the kinds of prompts students wrote.",
   "quote": "we conducted one of the first large-scale empirical studies examining how LLM use affects students' comprehension and retention",
   "location": "§1, p. 2"
  },
  "whoCares": {
   "summary": "Educators, schools and policymakers deciding how to bring AI tools into classrooms, and designers of LLM-based learning tools.",
   "quote": "The results are expected to provide valuable insights for education stakeholders and policymakers on thoughtfully integrating AI tools into schools",
   "location": "§2.4, p. 5"
  }
 },
 "researchQuestions": [
  "1) How does using an LLM for comprehension-focused reading affect students' text comprehension and retention compared to the more traditional learning activity of note-taking as well as compared to using an LLM alongside note-taking?",
  "2) How does using an LLM for comprehension-focused reading affect students' emotional, cognitive, and behavioural engagement compared to the more traditional learning activity of note-taking as well as compared to using an LLM alongside note-taking?",
  "3) What types of prompts do students use when interacting with the LLM?"
 ],
 "concepts": [
  {
   "term": "Reading retention",
   "definition": "The memory outcome, tested days after reading:",
   "quote": "Reading retention is the process of storing the comprehended content from a text in long-term memory.",
   "location": "§2.1, p. 2"
  },
  {
   "term": "Literal retention versus comprehension",
   "definition": "The study's two outcomes. Comprehension questions required inferences across the text and from prior knowledge. Literal retention questions did not:",
   "quote": "Literal retention questions (short response and multiple choice) required literal recall or recognition of information from the passage to provide a correct response.",
   "location": "§3.5.1, p. 7"
  },
  {
   "term": "Comprehension-focused reading",
   "definition": "Reading with active, constructive or interactive strategies, such as paraphrasing, making connections or dialogue with a partner.",
   "quote": "Note that the generation of questions (in this case LLM prompts) itself can be considered as a constructive process if the questions encourage students to think beyond the immediate text",
   "location": "§2.2.1, p. 3"
  },
  {
   "term": "Cognitive offloading to the LLM",
   "definition": "The risk that relying on an LLM for answers replaces the thinking that builds understanding.",
   "quote": "When learners depend excessively on LLMs for answers and explanations, they may be less inclined to employ self-explanation and elaboration strategies that are essential for comprehension and meaningful learning",
   "location": "§2.2.1, p. 3"
  }
 ],
 "method": {
  "design": "Pre-registered randomised controlled experiment with within- and between-participant design elements. Each student studied two history passages, each with a different activity: Group 1 used LLM and Notes, and Group 2 used LLM and LLM + Notes, with LLM as the common reference. A test session followed three days later.",
  "setting": "Seven secondary schools in England, during regular school hours, between March and July 2024. A custom chatbot based on GPT-3.5 turbo (maximum 20 prompts) and a notepad in a web app. Passages on Apartheid in South Africa and the Cuban Missile Crisis.",
  "sample": "405 Year 10 students aged 14-15. 344 retained for analysis (Group 1: 184, and Group 2: 160).",
  "n": 344,
  "duration": "Two sessions three days apart: a learning session (10 to 15 minutes per passage) and a test session.",
  "analysis": "Linear mixed-effects regressions for literal retention, comprehension and free recall, with students as a random effect and multiple imputation for missing covariates. Paired permutation tests for free recall. Paired t-tests with Bonferroni correction for engagement. GPT-4-assisted, human-checked qualitative coding of preference explanations and of 4929 prompts."
 },
 "findings": [
  {
   "headline": "Notes beat the chatbot.",
   "summary": "Three days after studying a history passage, 14-15-year-old students understood and remembered it better if they had taken notes, alone or alongside an AI chatbot, than if they had used the chatbot alone.",
   "quote": "students performed significantly better with Notes compared to LLM and with LLM + Notes compared to LLM for both literal retention and comprehension",
   "location": "§4.2, p. 12",
   "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s4-2-p-12",
   "cite": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514 (§4.2, p. 12)"
  },
  {
   "headline": "Notes alone did best.",
   "summary": "Note-taking alone also improved free recall, which notes alongside the chatbot did not. In an indirect, exploratory comparison, its advantage over the chatbot alone tended to be larger than that of the combined activity.",
   "quote": "For free recall, students showed significantly better performance with Notes compared to LLM but there was no significant difference between LLM + Notes compared to LLM.",
   "location": "§4.2, p. 12",
   "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s4-2-p-12-2",
   "cite": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514 (§4.2, p. 12)"
  },
  {
   "headline": "Enjoyed more, learned less.",
   "summary": "Compared with note-taking, students enjoyed the chatbot more, found it easier and rated it more helpful for understanding and learning the text, even though they scored lower after using it.",
   "quote": "Having an LLM do some of the work of summarising a passage or explaining a concept may feel more enjoyable and efficient but can reduce the cognitive engagement necessary for deep comprehension and long-term retention",
   "location": "§5, p. 16",
   "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s5-p-16",
   "cite": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514 (§5, p. 16)"
  },
  {
   "headline": "Less effort, and copied notes.",
   "summary": "With the chatbot alone, students reported less effort and spent slightly less time on the task, although time did not predict their scores. With chatbot and notepad together, about a quarter copied most of their notes straight from the chatbot's answers.",
   "quote": "This indicates that students' own note-taking efforts were reduced, and that the effectiveness of note-taking may be diminished.",
   "location": "§4.3.3, p. 15",
   "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s4-3-3-p-15",
   "cite": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514 (§4.3.3, p. 15)"
  },
  {
   "headline": "The combination was preferred.",
   "summary": "Students who tried both preferred the chatbot plus notes over the chatbot alone by a wide margin, and the combination did not reduce their enjoyment.",
   "quote": "Rather than viewing these as competing alternatives, we could think of them as complementary that, when thoughtfully integrated, may enhance learning outcomes in ways that neither can achieve alone.",
   "location": "§5, p. 17",
   "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s5-p-17",
   "cite": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514 (§5, p. 17)"
  },
  {
   "headline": "Curious questions, some off-topic.",
   "summary": "Students' prompts fell into four kinds, most often asking for more information and deeper understanding. Some explored ideas beyond the text, and about one in ten prompts were off-topic.",
   "quote": "in a passage on the Cuban Missile Crisis, another student asked, \"Why was America afraid of communism?\"",
   "location": "§5, p. 16",
   "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s5-p-16-2",
   "cite": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514 (§5, p. 16)"
  }
 ],
 "questions": [
  {
   "question": "Do students learn more from a text with an AI chatbot or by taking notes?",
   "answer": "Taking notes worked better in an experiment with 14-15-year-olds. Three days later, students who took notes, alone or alongside a chatbot, understood and remembered history texts better than those who used only the chatbot. The tests covered only the given texts, not broader learning.",
   "source": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514",
   "basedOn": [
    {
     "location": "§4.2, p. 12",
     "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s4-2-p-12"
    },
    {
     "location": "§4.2, p. 12",
     "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s4-2-p-12-2"
    }
   ]
  },
  {
   "question": "Can students tell which study methods help them learn?",
   "answer": "Perhaps not. Students enjoyed the chatbot more and rated it more helpful for understanding and learning than note-taking, yet scored lower after using it. The authors suggest students may have limited metacognitive knowledge of what helps them learn, and underweight the 'desirable difficulties' of effortful activities such as note-taking.",
   "source": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514",
   "basedOn": [
    {
     "location": "§5, p. 16",
     "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s5-p-16"
    }
   ]
  },
  {
   "question": "Why might studying with an AI chatbot lead to less learning?",
   "answer": "Possibly because the chatbot can do the work that builds understanding. Learning grows with cognitive engagement, and having a chatbot summarise or explain may feel easier but reduce it. Students reported less effort with the chatbot alone, and their prompts suggested they treated it mainly as a knowledgeable source.",
   "source": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514",
   "basedOn": [
    {
     "location": "§4.3.3, p. 15",
     "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s4-3-3-p-15"
    },
    {
     "location": "§5, p. 16",
     "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s5-p-16-2"
    }
   ]
  },
  {
   "question": "Does an AI chatbot have any learning benefits?",
   "answer": "Possibly, though not on the measures used. Students used it to clarify words, condense the text and ask about background, and some explored questions beyond the text, such as why America feared communism. Testing covered only the given texts, so that broader learning went unmeasured.",
   "source": "Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514",
   "basedOn": [
    {
     "location": "§5, p. 16",
     "url": "https://seanrintel.com/publications/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools.html#at-s5-p-16-2"
    }
   ]
  }
 ],
 "cites": [
  {
   "url": "https://seanrintel.com/publications/the-impact-of-generative-ai-on-critical-thinking-self-reported-reductions-in-cognitive-effort-and-confidence-effects-from-a-survey-of-knowledge-workers.html",
   "title": "The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge Workers",
   "location": "p. 23"
  },
  {
   "url": "https://seanrintel.com/publications/the-metacognitive-demands-and-opportunities-of-generative-ai.html",
   "title": "The Metacognitive Demands and Opportunities of Generative AI",
   "location": "p. 23"
  }
 ],
 "quantitative": [
  {
   "measure": "Sample",
   "value": "405 recruited; 344 analysed (Group 1: 184 students, 53.5 %; Group 2: 160, 46.5 %)",
   "location": "§3.2, p. 5"
  },
  {
   "measure": "Literal retention, Notes vs LLM",
   "value": "β = 1.92, t = 7.50, p < 0.001, d = 0.44",
   "location": "Table 3, p. 13"
  },
  {
   "measure": "Literal retention, LLM + Notes vs LLM",
   "value": "β = 0.57, t = 2.06, p = 0.040, d = 0.13",
   "location": "Table 3, p. 13"
  },
  {
   "measure": "Comprehension, Notes vs LLM",
   "value": "β = 0.95, t = 5.73, p < 0.001, d = 0.38",
   "location": "Table 3, p. 13"
  },
  {
   "measure": "Comprehension, LLM + Notes vs LLM",
   "value": "β = 0.35, t = 1.98, p = 0.048, d = 0.14",
   "location": "Table 3, p. 13"
  },
  {
   "measure": "Free recall, Notes vs LLM; LLM + Notes vs LLM",
   "value": "Notes: β = 1.02, p = 0.017, d = 0.21; LLM + Notes: p = 0.854 (not significant)",
   "location": "Table 3, p. 13"
  },
  {
   "measure": "Advantage of Notes over LLM + Notes (relative to LLM; indirect, exploratory comparison)",
   "value": "Literal retention: estimated mean difference = 1.35, z = 3.60, p < .001; comprehension: 0.59, z = 2.43, p = .015",
   "location": "§4.2, p. 12"
  },
  {
   "measure": "Activity preference",
   "value": "Group 1: LLM over Notes 42.0 %, Notes over LLM 26.9 %; Group 2: LLM + Notes over LLM 50.5 %, LLM over LLM + Notes 16.2 %",
   "location": "Table 4, p. 14"
  },
  {
   "measure": "Copying from LLM output into notes (LLM + Notes)",
   "value": "25.63 % of students over 70 % trigram overlap; 16.25 % over 90 %",
   "location": "§4.3.3, p. 15"
  },
  {
   "measure": "Prompts analysed; most frequent archetype",
   "value": "n = 4929; seeking additional information and deeper understanding, 2265 prompts",
   "location": "§4.4, p. 15"
  }
 ],
 "implications": [
  {
   "summary": "Separate LLM use from note-taking, or block pasting into the notepad, so that students synthesise information themselves.",
   "quote": "if the LLM and note-taking are used simultaneously, pasting into the notepad could be blocked",
   "location": "§5.1, p. 17"
  },
  {
   "summary": "Students need more comprehensive training to use LLMs in goal-focused ways aligned with active and constructive learning strategies. Software could also limit distracting, off-topic use."
  },
  {
   "summary": "Educators could use students' LLM prompts, in a privacy-protecting way, to see what concepts students struggle with or are curious about, and tailor lessons.",
   "quote": "educators could leverage insights from students' interactions with the LLM to better understand what concepts they are struggling with or what they are curious about",
   "location": "§5.1, p. 17"
  }
 ],
 "limitations": [
  {
   "summary": "Students received instructions and a demonstration but no in-depth training or practice, which may have disadvantaged the less familiar LLM conditions.",
   "quote": "One limitation of the present study is that students received no in-depth training for the different learning activities.",
   "location": "§5.2, p. 17"
  },
  {
   "summary": "There was no reading-only control condition, and Notes and LLM + Notes could be compared only indirectly, so that comparison needs caution.",
   "quote": "these comparison outcomes still need to be considered with caution because of the potential interaction effects (each group could have experienced the LLM differently)",
   "location": "§5.2, p. 18"
  },
  {
   "summary": "Qualitative coding was not independently double-coded, and prompts were analysed singly rather than as dialogues. Engagement used single-item measures."
  },
  {
   "summary": "A single, isolated learning activity with GPT-3.5 turbo, a model less advanced than more recent ones. Repeated or classroom use could yield different results.",
   "quote": "the study was limited to a single, isolated learning activity outside of the context of normal use throughout an entire course of study",
   "location": "§5.2, p. 18"
  }
 ],
 "figures": [
  {
   "src": "https://seanrintel.com/publications/figures/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools/fig-3.webp",
   "caption": "Fig. 3. Distribution of test performance by condition and group for comprehension, literal retention, and free recall. Mean values are indicated by the two large circles within each facet, whereas the smaller points show individual students' scores. Error bars indicate one standard error above and below the mean. Group 1 is shown on the left facet of each plot, comparing LLM (red) and Notes (blue). Group 2 is on the right facet of each plot, comparing LLM (red) and LLM + Notes (green). Comprehension (left, max 12 points): Group 1 - LLM: M = 4.00 (SD = 2.44), Notes: M = 4.89 (SD = 2.52); Group 2 - LLM: M = 3.80 (SD = 2.47), LLM + Notes: M = 4.11 (SD = 2.65). Literal retention (middle, max 20 points): Group 1 - LLM: M = 8.83 (SD = 3.96), Notes: M = 10.80 (SD = 4.29); Group 2 - LLM: M = 8.95 (SD = 4.29), LLM + Notes: M = 9.68 (SD = 4.83). Free recall (right, max 50 points): Group 1 - LLM: M = 4.32 (SD = 4.15), Notes: M = 5.36 (SD = 5.49); Group 2 - LLM: M = 4.32 (SD = 4.63), LLM +Notes: M = 4.20 (SD = 5.07). (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)",
   "alt": "Dot plots of individual scores and means. Notes beats LLM on comprehension (4.89 vs 4.00), literal retention (10.80 vs 8.83) and free recall (5.36 vs 4.32). LLM + Notes is slightly above LLM except on free recall.",
   "location": "Fig. 3, p. 10",
   "credit": "Figure 3 from Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514"
  },
  {
   "src": "https://seanrintel.com/publications/figures/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools/fig-4.webp",
   "caption": "Fig. 4. Differences in student engagement by group and condition. The top and middle panels show ratings for emotional and cognitive engagement measures, respectively, on a 1-5 scale. The bottom panel displays time on task, a behavioural engagement measure, in minutes. Each point represents the mean for a condition, with error bars indicating one standard error above and below the mean.",
   "alt": "Mean engagement ratings. Versus notes, the LLM is rated more enjoyable, less difficult and more helpful, with less effort and less time on task. Versus LLM + Notes, it is rated less difficult and used for less time.",
   "location": "Fig. 4, p. 13",
   "credit": "Figure 4 from Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514"
  },
  {
   "src": "https://seanrintel.com/publications/figures/effects-of-llm-use-and-note-taking-on-reading-comprehension-and-memory-a-randomised-experiment-in-secondary-schools/fig-5.webp",
   "caption": "Fig. 5. Distribution of student prompts across different types, showing the percentage of students who used the prompt type at least once (blue), as their most common prompt (magenta), and as their first prompt (green). Prompt types are arranged by overall frequency. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)",
   "alt": "Bar chart of prompt types by share of students. Seeking additional information and deeper understanding leads, used at least once by 90% and most often by 60%. Understanding the text was used by 70%, and study and memory help was rare.",
   "location": "Fig. 5, p. 15",
   "credit": "Figure 5 from Pia Kreijkes, Viktor Kewenig, Martina Kuvalja, Mina Lee, Jake Hofman, Sylvia Vitello, Abigail Sellen, Sean Rintel, Daniel G. Goldstein, David Rothschild, Lev Tankelevitch, and Tim Oates. 2025. Effects of LLM Use and Note-Taking On Reading Comprehension and Memory: A Randomised Experiment in Secondary Schools. Computers & Education. https://doi.org/10.1016/j.compedu.2025.105514"
  }
 ],
 "pageNumbersReferTo": "https://doi.org/10.1016/j.compedu.2025.105514",
 "verified": "2026-10-25",
 "studyFigure": {
  "about": "The opening figure on this paper's page, made for the site with AI assistance from this verified brief. It is not the paper's own figure. Evidence entries index this file's quantitative, findings and limitations arrays.",
  "study": {
   "kind": "comparison",
   "summary": "Preregistered randomised experiment with 344 Year 10 students aged 14 to 15 in seven secondary schools in England. Each studied two history passages, one with a GPT-3.5 chatbot alone.",
   "columns": [
    "One history passage",
    "The other passage"
   ],
   "groups": [
    {
     "name": "Notes group",
     "n": 184,
     "cells": [
      "AI chatbot alone",
      "Notes alone"
     ],
     "highlight": [
      1
     ]
    },
    {
     "name": "Chatbot and notes group",
     "n": 160,
     "cells": [
      "AI chatbot alone",
      "AI chatbot and notes"
     ],
     "highlight": [
      1
     ]
    }
   ],
   "after": {
    "label": "3 days later: test session",
    "note": "Literal retention, comprehension and free recall for both passages"
   }
  },
  "findings": {
   "legend": "comparison",
   "stages": [
    {
     "title": "3 days later",
     "sub": "each group's other passage compared with its chatbot alone passage",
     "items": [
      {
       "dir": "up",
       "text": "Notes group: understood and remembered more after taking notes than after the chatbot alone.",
       "detail": "Small to moderate effects, d = 0.44 for literal retention and d = 0.38 for comprehension.",
       "evidence": [
        "quantitative[1]",
        "quantitative[3]",
        "findings[0]"
       ]
      },
      {
       "dir": "up",
       "text": "Chatbot and notes group: understood and remembered more when notes were added to the chatbot.",
       "detail": "Very small effects, d = 0.13 for literal retention and d = 0.14 for comprehension.",
       "evidence": [
        "quantitative[2]",
        "quantitative[4]",
        "findings[0]"
       ]
      },
      {
       "dir": "up",
       "text": "Notes group: freely recalled more of the passage after taking notes.",
       "detail": "A small effect, d = 0.21. In the chatbot and notes group, free recall did not differ reliably from the chatbot alone.",
       "evidence": [
        "quantitative[5]",
        "findings[1]"
       ]
      }
     ]
    },
    {
     "title": "During learning",
     "sub": "ratings, preferences, notes and prompts",
     "items": [
      {
       "dir": "down",
       "text": "Notes group: rated note-taking less enjoyable and less helpful than the chatbot alone.",
       "detail": "Self-reported. Students also found the chatbot easier, yet scored lower after using it.",
       "evidence": [
        "findings[2]"
       ]
      },
      {
       "dir": "none",
       "text": "Notes group: 42.0% preferred the chatbot alone and 26.9% preferred notes.",
       "detail": "Self-reported preference between the two activities.",
       "evidence": [
        "quantitative[7]"
       ]
      },
      {
       "dir": "none",
       "text": "Chatbot and notes group: 50.5% preferred chatbot and notes, and 16.2% the chatbot alone.",
       "detail": "Self-reported preference. Adding notes did not reduce enjoyment.",
       "evidence": [
        "quantitative[7]",
        "findings[4]"
       ]
      },
      {
       "dir": "none",
       "text": "Chatbot and notes group: about a quarter copied most of their notes from the chatbot.",
       "detail": "For 25.63% of students, over 70% of three-word sequences in their notes matched the chatbot's answers.",
       "evidence": [
        "quantitative[8]",
        "findings[3]"
       ]
      },
      {
       "dir": "none",
       "text": "Both groups: prompts most often asked the chatbot for more information and deeper understanding.",
       "detail": "Of 4929 prompts, 2265 did so. About one in ten prompts were off-topic.",
       "evidence": [
        "quantitative[9]",
        "findings[5]"
       ]
      }
     ]
    }
   ],
   "legendText": "↑ better than the same students with the AI chatbot alone   ↓ worse   – no reliable difference"
  },
  "keyTerm": "cognitive engagement",
  "takeaway": "Taking notes can help students understand and remember texts better than using a chatbot alone. Summarising in their own words demands cognitive engagement, while a chatbot may do that work for them and feel easier."
 }
}