[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-585323-105":59,"doc-detail-585323-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","ai-powered-teacher-assistance-for-inclusive-education","AI-POWERED TEACHER ASSISTANCE FOR INCLUSIVE EDUCATION","","Inclusive classrooms require continuous individualized support that is difficult to scale across diverse learners. This paper proposes an AI-powered teacher assistant enabling early identification of student needs and timely accommodations. The architecture ingests multimodal classroom data such as assignments, quiz results, and reading assessments, and connects it to a retrieval-augmented knowledge base grounded in standards. Large language models support learner modeling and recommendations, while an orchestration layer enforces privacy constraints. A teacher dashboard provides regulation-aligned summaries, explanations, and actions the teacher can accept, reject, or edit, addressing bias, explainability, governance, and compliance.",{"@graph":69,"@context":122},[70,84,105],{"@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/ai-powered-teacher-assistance-for-inclusive-education/585323/",{"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/ai-powered-teacher-assistance-for-inclusive-education/585323.png","ImageObject",300,407,{"name":92,"@type":93},"Aria Callaghan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-10","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the AI-powered teacher assistant address in inclusive education?","Question",{"text":112,"@type":113},"It targets the difficulty of providing continuous, individualized support to large numbers of students, by helping educators identify needs early and intervene sooner.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed system use classroom information to support teachers?",{"text":117,"@type":113},"It ingests multimodal data such as assignments, quiz results, and reading assessments, then links these signals to a retrieval-augmented knowledge base of standards to generate recommendations.",{"name":119,"@type":110,"acceptedAnswer":120},"What mechanisms are included to handle privacy and teacher control?",{"text":121,"@type":113},"An orchestration layer enforces privacy constraints and routes relevant information only. The teacher dashboard presents summaries and recommendations aligned with regulations, and the teacher can accept, reject, or edit them.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},585323,1792054382,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":19,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":52,"preview_page_count":4},962084926284,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","AI-POWERED TEACHER ASSISTANCE FOR INCLUSIVE  \nEDUCATION  \nRita Nohra and Mohamad Al Assaad  \nTalan Research and Innovation Center  \nParis, France  \nABSTRACT  \nInclusive classrooms demand continuous, individualized support that is difficult to deliver on a scale. This paper proposesan AI‑powered teacher assistant that helps educators identify student needs early and therefore accommodate the students accordingly. This paper shows an architecture that ingests multimodal classroom data (e.g., assignments, quiz results, reading assessments) and links it to a retrieval‑augmented knowledge base of standards. It uses large language models (LLMs) for learner modeling and recommendations. An orchestration layer enforces privacy constraints and routes only relevant information. The teacher dashboard shows summaries, explanations, and recommendations aligned with regulations and best practices. The teacher can then accept, reject, or edict those suggestions. Ethical and practical considerations, including bias, explainability, governance, and compliance, are addressed through.  \nKEYWORDS  \nRAG (Retrieval Augmented Generation), Teacher Assistant, Inclusive Education, Artificial Intelligence  \n1. INTRODUCTION  \nInclusive education is essential to ensure that all students have fair access to learning opportunities, regardless of their backgrounds, abilities, or neurocognitive differences. It requires recognizing that learning needs differ from each student and then provide adequate support. To be able to achieve that, classrooms require constant monitoring. However, in practice, it is hard for teachers to manage large classrooms while trying to observe, assess, and intervene early for every student exhibiting learning difficulty. Globally, an estimated 240 million children have disabilities, and about half of them are out of school. Even those in school may lack adequate support (World Health Organization and United Nations Children's Fund, 2023) .  \nRecent advances in artificial intelligence, particularly large language models (LLMs) and multimodal AI systems, have shown promising advances to scale up individualized educational support. Unlike traditional educational technologies, LLMs can process natural language, analyze student-generated data, and generate feedback. They can act as a “teaching assistant” by helping educators identify learning patterns, detect difficulties, and design personalized instructions (Fitas, 2025) .  \nWang et al. (2025) introduced an LLM-based system that generates personalized learning plans and provides real-time support within online learning environments. Similarly, Tonga et al. (2025) demonstrated that multilingual feedback generated by LLMs can enhance mathematical learning, particularly in languages with limited resources. Melo-López et al. (2025) found that AI can enhance accessibility by providing adapted materials for students with visual or hearing impairments, support easier personalization and reduce teacher workload. A review entitled The Integration of Artificial Intelligence in Inclusive Education (2024) also demonstrated the importance of evaluating AI-driven interventions in real-world inclusive classrooms.  \nMa et al. (2024) developed the SOEI framework, which enables virtual student agents with diverse learning profiles to help teachers anticipate varied classroom needs. Similarly, Bewersdorff et al. (2024) examined the role of multimodal large language models in education. The study highlights how AI systems that handle both text and visual information can provide more interactive and accessible feedback.  \nThese works illustrate the potential and challenges of adopting AI inclusive education. On the one hand, there is the promise of early detection of difficulties, personalized feedback loops, and accommodating linguistic and sensory diversity. On the other hand, there are persistent issues such as bias, data privacy, teacher training, infrastructure, and ensuring that human oversight rema","cbCaiuJo8QRx9Faa","https://ap.wps.com/l/cbCaiuJo8QRx9Faa","pdf",776817,"English","# Abstract\n# 1. INTRODUCTION\n## Inclusive education needs and classroom monitoring\n## Prior work using LLMs and AI for personalization and accessibility\n## Opportunities and challenges for AI in inclusive education\n# 2. METHODOLOGY\n## Bias and fairness\n## Privacy in handling student data\n## Local or on-device approaches","[{\"question\":\"What problem does the AI-powered teacher assistant address in inclusive education?\",\"answer\":\"It targets the difficulty of providing continuous, individualized support to large numbers of students, by helping educators identify needs early and intervene sooner.\"},{\"question\":\"How does the proposed system use classroom information to support teachers?\",\"answer\":\"It ingests multimodal data such as assignments, quiz results, and reading assessments, then links these signals to a retrieval-augmented knowledge base of standards to generate recommendations.\"},{\"question\":\"What mechanisms are included to handle privacy and teacher control?\",\"answer\":\"An orchestration layer enforces privacy constraints and routes relevant information only. The teacher dashboard presents summaries and recommendations aligned with regulations, and the teacher can accept, reject, or edit them.\"}]","AI-POWERED TEACHER ASSISTANCE FOR INCLUSIVE EDUCATION | PDF"]