[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86329-en":3,"doc-seo-86329-105":28,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":11},86329,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Supporting Reflection in LLM-based Exploratory Search","Large Language Models (LLMs) can make exploratory search faster, yet they may weaken the reflection and iterative sensemaking needed when users explore unfamiliar domains. Many existing LLM tools optimize for quick answers instead of helping people track how understanding develops and whether strategies match their goals. TrailLM addresses this by enabling users to reconstruct and revisit exploration paths, strengthening metacognitive engagement and critical reflection during information seeking.","Supporting Reflection in LLM-based Exploratory Search  \nGiulia Di Fede  \nPolitecnico di Milano Milan, Italy [giulia.difede@polimi.it](giulia.difede@polimi.it)  \nSalvatore Andolina Politecnico di Milano  \nMilan, Italy [salvatore.andolina@polimi.it](salvatore.andolina@polimi.it)  \narXiv :2607 . 11810v1 [ cs .HC] 13 Jul 2026  \nAbstract  \nLarge Language Models (LLMs) can make exploratory search more efficient but may undermine the reflection and iterative sensemaking needed in unfamiliar domains. Existing LLM tools often prioritize rapid answers over supporting users in tracking how their understanding evolves and how well their strategies align with their goals. We present TrailLM, a system that helps users reconstruct and revisit their exploration paths to support reflection and metacognitive engagement during information seeking. By aligning LLM assistance with users’ sensemaking workflows, TrailLMaims to preserve the benefits of LLM-based search while enhancing opportunities for critical reflection on one’s own search process.  \nCCS Concepts  \n• Human-centered computing → Interaction design theory, concepts and paradigms; HCI theory, concepts and models; • Information systems → Information retrieval.  \nKeywords  \nExploratory Search, Critical Thinking, Meta-Cognition, Information Retrieval, Generative Artificial Intelligence, Large Language Models  \nReference:  \nGiulia Di Fede and Salvatore Andolina. 2026. Supporting Reflection in LLMbased Exploratory Search. In CHI 2026 BiAlign Workshop. ACM, New York, NY, USA, 3 pages.  \n1 Introduction  \nExploratory search is a cognitively demanding task characterized by vague and evolving information needs [8] . Unlike lookup searches such as \"How tall is Obama?\", which rely on well-defined queries and can be answered instantly, exploratory search involves iterative query reformulation, multiple open tabs, and prolonged sessions that may span hours, days, or weeks. Tasks like planning a vacation or researching a new topic require users to discover new keywords, refine goals, and issue increasingly precise queries in a continuous, cognitively intense process of exploration and sensemaking [9] .  \nThe advent ofLLMs is transforming exploratory search, promising more efficient retrieval and summarization of relevant information. Yet users often struggle to translate their goals into the detailed prompts needed to use these systems effectively [11] . This is especially true in the early stages of exploratory search when  \nThis work is licensed under a Creative Commons Attribution-NonCommercialNoDerivatives 4 .0 International License.  \nCHI 2026 BiAlign Workshop, Barcelona, Spain © 2026 Copyright held by the owner/author(s) .  \nintent is still vague and users are forming their needs and understanding of the information space. In more traditional exploratory search approaches, users iteratively refine queries, compare sources, and revise their information-seeking goals [2, 3, 6] . In LLM-based search, by contrast, users receive a direct answer to an initial, often underdeveloped prompt, which may encourage them to bypass the critical process of iterative sensemaking. Consequently, they may obtain incomplete or misleading responses that fail to match their actual needs [1] . In addition, LLMs can generate false information that appears authoritative, known as hallucinations, and reinforce biases embedded in their training data. When users rely on LLMs without making the effort to iteratively make sense of the information space, they could face inhibition of reflection or critical thinking [5, 7] and incur the risk of more easily accepting information that is incomplete, inaccurate, or biased [4] .  \nTo understand how to support reflection in LLM-based exploratory search, we focus on metacognition—the ability to reflect on and regulate one’s own thinking—which is increasingly central to designing aligned human–AI interactions [7, 10]. In exploratory search, users must reflect on their metacognitive p","cbCaie6b9O3i8FtL","https://ap.wps.com/l/cbCaie6b9O3i8FtL","pdf",1020523,1,3,"English","en",105,"# Introduction\n## Exploratory Search Challenges\n## LLM Impact and Risks\n# TrailLM\n## Design Goals\n## Goal Alignment Monitoring","[{\"question\":\"What problem does the document address in LLM-based exploratory search?\",\"answer\":\"LLM tools can undermine reflection and iterative sensemaking, causing users to bypass critical exploration and accept incomplete or misleading responses.\"},{\"question\":\"What is TrailLM’s main purpose?\",\"answer\":\"TrailLM helps users reconstruct and revisit their exploration paths so they can support metacognitive reflection and stay engaged with the search process.\"},{\"question\":\"How does TrailLM support alignment with user goals?\",\"answer\":\"It externalizes the system’s interpretation of self-defined subgoals as a visible goal state, making active subgoals explicit so users can reflect, adjust, and add or revise subgoals over time.\"}]",1784210508,{"code":4,"msg":29,"data":30},"ok",{"site_id":24,"language":23,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"supporting-reflection-in-llm-based-exploratory-search","",{"@graph":34,"@context":83},[35,51,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,48],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":21},"https://docshare.wps.com/document/research-report/",{"item":49,"name":13,"@type":41,"position":50},"https://docshare.wps.com/document/supporting-reflection-in-llm-based-exploratory-search/86329/",4,{"url":49,"name":13,"@type":52,"author":53,"headline":13,"publisher":55,"fileFormat":58,"inLanguage":23,"description":14,"dateModified":59,"datePublished":60,"encodingFormat":58,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":54},"Person",{"url":39,"name":56,"@type":57},"DocShare","Organization","application/pdf","2026-07-22","2026-07-16",true,{"@type":63,"interactionType":64,"userInteractionCount":20},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the document address in LLM-based exploratory search?","Question",{"text":73,"@type":74},"LLM tools can undermine reflection and iterative sensemaking, causing users to bypass critical exploration and accept incomplete or misleading responses.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What is TrailLM’s main purpose?",{"text":78,"@type":74},"TrailLM helps users reconstruct and revisit their exploration paths so they can support metacognitive reflection and stay engaged with the search process.",{"name":80,"@type":71,"acceptedAnswer":81},"How does TrailLM support alignment with user goals?",{"text":82,"@type":74},"It externalizes the system’s interpretation of self-defined subgoals as a visible goal state, making active subgoals explicit so users can reflect, adjust, and add or revise subgoals over time.","https://schema.org",{"og:url":49,"og:type":85,"og:title":13,"og:site_name":56,"og:description":14},"article",{"robots":87,"canonical":49},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":50,"doc_module":4,"doc_module_name":44,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":44,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":44,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":44,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":44,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":44,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":44,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":44,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]