[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273368-105":59,"doc-detail-273368-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","when-looks-do-not-lie-discourse-structure-guided-in-context-learning-for-faithful-diagram-generation","When Looks Do Not Lie - Discourse Structure Guided In-Context Learning for Faithful Diagram Generation","","GenAI is widely used in educational settings yet can produce intrinsic and extrinsic hallucinations that undermine learning quality. The paper proposes a new ICL method for diagram generation grounded in Rhetorical Structure Theory, increasing faithfulness to the given source-text context. Results show ICL quality depends on task distribution and model reasoning ability, with stronger reasoning improving out-of-distribution performance. Expert evaluation of 150 diagrams and Bayesian GLMM analysis assess hallucination and consistency, and an automated rubric achieves significant agreement with humans.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/when-looks-do-not-lie-discourse-structure-guided-in-context-learning-for-faithful-diagram-generation/273368/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/when-looks-do-not-lie-discourse-structure-guided-in-context-learning-for-faithful-diagram-generation/273368.png","ImageObject",300,407,{"name":92,"@type":93},"Himbo","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address in educational diagram generation?","Question",{"text":113,"@type":114},"The paper targets intrinsic and extrinsic hallucinations in GenAI-based learning materials, which can lead to unfaithful or inaccurate diagrams that misinform learners.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed method improve diagram faithfulness?",{"text":118,"@type":114},"It uses Discourse Structure Guided In-Context Learning based on Rhetorical Structure Theory to select informative in-context examples and provide a consistent hierarchical pattern for generation.",{"name":120,"@type":111,"acceptedAnswer":121},"What evidence supports the method’s effectiveness?",{"text":122,"@type":114},"The study performs expert evaluation of 150 generated diagram-text pairs and analyzes the findings with Bayesian GLMMs, showing reduced source-context inconsistency and improved fidelity when reasoning ability is higher.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},273368,1789471095,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},687197100911,"https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697","When Looks Do Not Lie: Discourse Structure Guided In-Context Learning  \nfor Faithful Diagram Generation  \nEvanfiya Logacheva1 , Arto Hellas1 , Tsvetomila Mihaylova1 , Juha Sorva1 , Ava Heinonen1 , Juho Leinonen1  \n1Aalto University,  \n{evanfiya.logacheva, arto.hellas, tsvetomila.mihaylova, juha.sorva, ava.heinonen, juho.2.leinonen}@aalto.fi  \narXiv : 260 1 .20476v2 [cs .CL] 2 1 Aug 2026  \nAbstract  \nGenAI is widespread in educational applications; however, it is known to generate content with intrinsic and extrinsic hallucination.  \nWe introduce a novel method for ICL diagram generation based on Rhetorical Structure Theory, which improves diagram faithfulness to its source text context. We find that ICL performance depends on task distribution and models’ reasoning ability, with higher reasoning allowing better quality and performance for an out-of-distribution task. We perform an expert evaluation of 150 generated diagrams and analyze our findings using Bayesian GLMMs.  \nAdditionally, we use our evaluation rubric and samples from the data set for automated diagram evaluation, achieving statistically significant agreement with human evaluation.  \n1 Introduction  \nDiagram code generation 1 from a given context is not a straightforward task for large language models (LLMs) as it involves context parsing and generation of syntactically correct code. Recent works use such approaches as entity and relation extraction for flowchart generation in a chatbot (Jiang et al., 2023) and information extraction using a user’s intent alongside in-context learning (ICL) (Mondal et al., 2024) for science diagram construction. Fully automated systems for diagram generation require even more sophisticated approaches as an LLM would need to determine a possible user intent from a given context and infer the correct type of a diagram, e.g. a flowchart vs a tree. In addition to this, AI-powered systems need to stay faithful to the context they are given to minimize both intrinsic and extrinsic hallucination (Huang et al., 2025 ; Ravichander et al., 2025) . This presents a unique challenge for diagram generation in educational contexts, as hallucination  \n1 Generation of code that is rendered or displayed as a diagram, e.g., using the Graphviz library.  \nin generated learning materials present a considerable risk to learners (Bernstein et al., 2025) . While AI-generated diagrams may appear superficially acceptable, factual hallucination or unfaithfulness to course materials lead to irrelevant or inaccurate information presented to students, which is a highly undesirable behavior in automated pipelines integrated in online learning. Our study introducesa novel method for diagram generation with ICLaimed to maintain consistency with user expectations for high quality and to minimize the occurrence of AI hallucination. We investigate our method as a proof of concept to estimate its feasibility and uncover both weaknesses and strengths for future applications.  \nThe performance of ICL relies on the ability of LLMs to overcome the distributional mismatch between their pre-training prior and a given prompt, which is achieved when examples within the prompt are informative enough for a model to infer concepts present in its pre-training (Xie et al., 2022) . Rhetorical Structure Theory (RST) (Mann and Thompson, 1988) has been earlier adopted for measuring discourse structure similarity (Joty et al., 2017) and creation and analysis of multimedia content (André and Rist, 1995 ; Bateman et al., 2001 ; Hiippala et al., 2020) . Discourse structure representation with RST serves for both selection of relevant in-context examples through discourse structure similarity, which would guide LLMs towards the correct type of a diagram, and implicit demonstration of the hierarchical discourse structure a text should be mapped into. By providing a nested diagrammatic representation as an example, it allows the model to generate a diagram that is faithful to the provided pr","cbCaif70524MpDj8","https://ap.wps.com/l/cbCaif70524MpDj8","pdf",1240622,31,"English","# Abstract\n# Introduction\n# Background\n## Rhetorical Structure Theory","[{\"question\":\"What problem does the paper address in educational diagram generation?\",\"answer\":\"The paper targets intrinsic and extrinsic hallucinations in GenAI-based learning materials, which can lead to unfaithful or inaccurate diagrams that misinform learners.\"},{\"question\":\"How does the proposed method improve diagram faithfulness?\",\"answer\":\"It uses Discourse Structure Guided In-Context Learning based on Rhetorical Structure Theory to select informative in-context examples and provide a consistent hierarchical pattern for generation.\"},{\"question\":\"What evidence supports the method’s effectiveness?\",\"answer\":\"The study performs expert evaluation of 150 generated diagram-text pairs and analyzes the findings with Bayesian GLMMs, showing reduced source-context inconsistency and improved fidelity when reasoning ability is higher.\"}]","When Looks Do Not Lie - Discourse Structure Guided In-Context Learning for Faithful Diagram Generation | PDF",78]