[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-517276-105":59,"doc-detail-517276-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","loremaster-towards-better-mixed-initiative-content-co-creation-in-the-creative-industries","Loremaster - Towards Better Mixed-Initiative Content Co-Creation in the Creative Industries","","Introduces early designs and prototypes for a human-AI co-creative system targeting the creative industries, especially entertainment, where reproductive storytelling (remakes, sequels, adaptations) draws from existing creative lore. The system uses retrieval-augmented generation (RAG) and large multimodal models to guide generative outputs with creative direction documents and complex narrative constraints. Initial text and 2D image applications show promising results, with future work focused on broader testing and improved narrative and visual accuracy in diverse contexts.",{"@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/loremaster-towards-better-mixed-initiative-content-co-creation-in-the-creative-industries/517276/",{"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/loremaster-towards-better-mixed-initiative-content-co-creation-in-the-creative-industries/517276.png","ImageObject",300,407,{"name":92,"@type":93},"OmBimo","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-20","2026-10-07",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address in generative AI for creative industries?","Question",{"text":113,"@type":114},"It addresses how to ensure generative AI outputs align with pre-existing creative lore when supporting reproductive storytelling projects like remakes, sequels, and adaptations.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed system guide human-AI co-creative output?",{"text":118,"@type":114},"It leverages retrieval-augmented generation (RAG) with large language models and large multimodal models, using creative direction documents to constrain and guide generation within established boundaries.",{"name":120,"@type":111,"acceptedAnswer":121},"What initial applications and evaluation are reported?",{"text":122,"@type":114},"The authors test the system for text and 2D image generation and report initial user insights (n=2) for further development.","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},517276,1791519188,{"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":24,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},962090893581,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Loremaster: Towards Better Mixed-Initiative Content Co-Creation in the Creative Industries  \nOLIVER WOOD, Those Beyond, United Kingdom  \nWe present early designs and prototypes for a human-AI co-creative system designed for the creative industries, notably entertainment industries. We specifically address the surge in reproductive storytelling works such as remakes, sequels, and adaptations. Our system leverages retrieval-augmented generation (RAG) and large multimodal models (LMMs) to ensure that generative AI outputs adhere to existing complex creative lore, leveraging and fine-tuning creative direction documents for guidance. Initial applications in text and 2D image generation have yielded promising results. We work towards effectively integrating generative AI within production workflows for the creative and entertainment industries, with future work focusing on extensive testing, improving narrative and visual content accuracy within a broad range of creative contexts.  \nCCS Concepts: • Applied computing → Arts and humanities; • Human-centered computing → Human computer interaction (HCI); • Computing methodologies → Artificial intelligence.  \nAdditional KeyWords and Phrases: Human-AI co-creation, Mixed initiative co-creation, Creative industries, Game design, Entertainment  \n1 INTRODUCTION  \nReproductions, remakes, reboots, prequels, sequels, spin-offs, and adaptions. These forms of media-referred to in this work as reproductive storytelling-all have different attributes, but share a key feature: creating from pre-existing stories, narratives, and creative lore. In film, there has been an influx in popularity of reproductive storytelling: with 90% of top grossing box office productions worldwide between 2021-2022 being remakes, sequels, spin offs, and adaptions. [16] This influx of reproductive media is likewise noticeable in the games industry: with high profile reproductive games-such as Baldur’s Gate 3, Dead Space, Resident Evil 4, Warhammer 40K: Boltgun [13], and many more being released by large and small studios alike. [3] It’s safe to say that reproductive storytelling is significant in the current creative industries, particularly entertainment. This poses a new design challenge for employing generative AI in the creative industries-if we ask creatives (art directors, game designers, animators, etc) to use a system which delivers a different outcome for each generated object, how can they ensure that generative outcomes are in line with the pre-existing creative lore with which they are working? We contribute initial designs and early prototypes for a human-AI co-creative system oriented to assist creatives working on reproductive storytelling projects in industry. Leveraging retrieval-augmented generation (RAG) [9] with large language models (LLMs) and multimodal large language models (also known as LMMs or MLLMs)  \n[20], our system introduces a unique concept: employing a creative direction document, or series of documents to guidegenerative content output according to pre-existing creative boundaries. We test our system on text and 2D image and gain initial user insights (n=2) for further development. Our work is oriented towards game design: however, this system can be applied to any context in which creatives employ generative AI whilst working within specific creative boundaries.  \n2 SURROUNDING WORK  \n2.1 Mixed initiative and human-AI co-creativity  \nThis work is situated in the fields of human-AI co-creativity (HAI-CC) and mixed-initiative co-creativity (MI-CC) . Although mixed initiative is not clearly defined [8], this paper refers to mixed initiative co-creativity as a collaborative  \nLicensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Copyright remains with the author(s) .  \nGenAICHI: CHI 2024 Workshop on Generative AI and HCI 1  \nprocess where both human and computational participants actively contribute to solving a problem, such as generating content [19] . This mea","cbCaia7UegCQuDwO","https://ap.wps.com/l/cbCaia7UegCQuDwO","pdf",410366,"English","# INTRODUCTION\n## Mixed initiative and human-AI co-creativity\n## Mixed initiative and co-creative systems with game design applications","[{\"question\":\"What problem does the paper address in generative AI for creative industries?\",\"answer\":\"It addresses how to ensure generative AI outputs align with pre-existing creative lore when supporting reproductive storytelling projects like remakes, sequels, and adaptations.\"},{\"question\":\"How does the proposed system guide human-AI co-creative output?\",\"answer\":\"It leverages retrieval-augmented generation (RAG) with large language models and large multimodal models, using creative direction documents to constrain and guide generation within established boundaries.\"},{\"question\":\"What initial applications and evaluation are reported?\",\"answer\":\"The authors test the system for text and 2D image generation and report initial user insights (n=2) for further development.\"}]","Loremaster - Towards Better Mixed-Initiative Content Co-Creation in the Creative Industries | PDF",1791337818,13,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/59b57ca147c958bb17c7f285780b48a7.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/f0178b91a50b6638c6990948f3b07ea6.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/93118056746a35960fade8990c5295e9.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/da221c638384574b656896e891fcc52b.webp",980,1268]