[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83933-en":3,"doc-seo-83933-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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":28},83933,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",6,"Technology","ChatImage Navigating Long-Form LLM Answers through Interactive Images","Large Language Models can answer complex queries, yet their long-form responses are delivered as dense linear text that hinders fine-grained inspection and revisiting. ChatImage converts long answers into interactive visual images by normalizing text into structured visual modules, planning a layout, and rendering a coherent image. A second vision-grounding pass (e.g., LocateAnything, MiMo-Vision, optional SAM-style refinement) grounds visible regions and overlays transparent clickable hotspots, each opening region-scoped detail and follow-up threads. This generate-then-ground alignment improves consistency between rendered visuals and interactive targets, and is evaluated with a 30-question benchmark plus alignment diagnostics.","arXiv :2607 .05290v 1 [ cs .CV] 6 Jul 2026  \nChatImage: Navigating Long-Form LLM Answers through Interactive Images  \nWencan Jiang1 , Jiangning Zhang1, , Yong Liu1  \n1 Zhejiang University  \nLarge Language Models (LLMs) can produce detailed answers to complex queries, but these answers are typically presented as dense linear text, which makes fine-grained inspection, navigation, and return visits difficult. We present ChatImage, a system that converts long-form LLM answers into interactive visual images. Given a textual answer, ChatImage first normalizes its content into structured visual modules, plans a visual layout, and renders a coherent image. It then applies a second grounding pass to the rendered image with vision grounding models such as LocateAnything and MiMo-Vision, with optional SAM-style mask refinement, to identify the visible regions that should support interaction. From these grounded regions, ChatImage overlays transparent clickable hotspots on the image. Each hotspot opens a detail panel and a region-scoped follow-up thread, allowing the user to inspect and query a specific part of the answer without re-reading the full response. Instead of treating planned coordinates as the final interaction geometry, ChatImage uses them as priors and grounds the interaction targets after rendering, which improves consistency between visual content and clickable regions. We release a reference implementation and introduce a 30-question benchmark covering infographic, map, and scene-based answer formats. Evaluation with configured external models reports interaction-loop completion, a strict visual-alignment gate, and a SAM-based mask-completeness diagnostic.  \nDate: July 7, 2026  \n Correspondence: [186368@zju.edu.cn](186368@zju.edu.cn)  \nCode: [github.com/wencanjiang/ChatImage](github.com/wencanjiang/ChatImage)[ ](github.com/wencanjiang/ChatImage)Project: [wencanjiang.github.io/ChatImage](wencanjiang.github.io/ChatImage)  \n1 Introduction  \nLarge Language Models (LLMs) have become a common interface for answering complex questions [1, 26] . Their answers, however, are still delivered mainly as extended prose. This format is effective for short factual queries, but it becomes less suitable when an answer contains internal structure, such as multiple entities, comparisons, procedural stages, or spatial relations. In such cases, readers often need to locate a specific module, inspect its context, and return to it later. Plain text can encode this information, but it provides limited support for navigation.  \nRecent progress in text-to-image generation [27, 28 , 31] and vision-language understanding [4, 18] suggests a complementary presentation format: rendering the answer as an image. A generated infographic, map, or scene can expose modules, hierarchies, routes, and spatial relationships in a single view. Static images, however, lose the explanatory structure associated with each region and provide no mechanism for region-level follow-up. A direct overlay of planned boxes is also unreliable, because image generators do not consistently place content at the requested coordinates [6, 8] . If the interaction layer is copied from the pre-generation layout, a user may click an empty region or an unintended visual element.  \nWe propose ChatImage, a system that converts a long-form LLM answer into an interactive visual image: a generated image with transparent hotspots placed over visible answer regions (Figure 1) . Each hotspot opens the explanation associated with that region and maintains a local follow-up thread. The central technical problem is alignment: a hotspot should cover the object, panel, landmark, or diagram region visible to the user, rather than the box specified before image generation.  \nFigure 1 ChatImage turns a long-form LLM answer into an interactive visual image. Given a user question, ChatImage generates an image whose regions are clickable hotspots. Each hotspot opens a detail panel with the region’s explanat","cbCaisF00FSBV6TE","https://ap.wps.com/l/cbCaisF00FSBV6TE","pdf",3506280,1,10,"English","en",105,"# Introduction\n## Interactive visual answers\n## Generate-then-ground alignment\n## Reference implementation\n## Benchmark and grounding evaluation","[{\"question\":\"Why are long-form LLM answers difficult to navigate in plain text?\",\"answer\":\"Their dense linear prose makes it hard to inspect internal structure such as multiple entities, comparisons, procedural stages, and spatial relations, and it also makes returning to a specific module inconvenient.\"},{\"question\":\"How does ChatImage turn a text answer into an interactive visual image?\",\"answer\":\"It first normalizes the textual answer into structured visual modules, plans a visual layout, and renders an image. Then it runs a second vision grounding pass to localize rendered regions and overlays transparent clickable hotspots.\"},{\"question\":\"How does ChatImage ensure hotspots align with the correct visual regions?\",\"answer\":\"Rather than using planned coordinates as final interaction geometry, it treats them as priors and re-grounds the interaction targets after rendering using vision grounding models, with optional SAM-style mask refinement to improve region coverage and consistency.\"}]",1784191528,25,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"chatimage-navigating-long-form-llm-answers-through-interactive-images","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/chatimage-navigating-long-form-llm-answers-through-interactive-images/83933/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why are long-form LLM answers difficult to navigate in plain text?","Question",{"text":74,"@type":75},"Their dense linear prose makes it hard to inspect internal structure such as multiple entities, comparisons, procedural stages, and spatial relations, and it also makes returning to a specific module inconvenient.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does ChatImage turn a text answer into an interactive visual image?",{"text":79,"@type":75},"It first normalizes the textual answer into structured visual modules, plans a visual layout, and renders an image. Then it runs a second vision grounding pass to localize rendered regions and overlays transparent clickable hotspots.",{"name":81,"@type":72,"acceptedAnswer":82},"How does ChatImage ensure hotspots align with the correct visual regions?",{"text":83,"@type":75},"Rather than using planned coordinates as final interaction geometry, it treats them as priors and re-grounds the interaction targets after rendering using vision grounding models, with optional SAM-style mask refinement to improve region coverage and consistency.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,112,117,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":45,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":21,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]