[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-514980-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-514980-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","simulating-hp-lovecraft-horror-literature-with-chatgpt-3","Simulating H.P. Lovecraft horror literature with ChatGPT 3","","This paper presents a novel method for simulating H.P. Lovecraft’s horror literature using the ChatGPT large language model, focusing on the GPT-4 architecture. It generates text that emulates Lovecraft’s distinctive writing style and themes while evaluating how prompt engineering steers model outputs. A curated prompt with specialized literature references is used, and the generated text is empirically assessed via an undergraduate student survey and statistical hypothesis testing.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/simulating-hp-lovecraft-horror-literature-with-chatgpt-3/514980/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/simulating-hp-lovecraft-horror-literature-with-chatgpt-3/514980.png","ImageObject",300,407,{"name":42,"@type":43},"Nguyễn Văn Học","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-17","2026-10-06",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",17,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"How does the paper simulate H.P. Lovecraft’s horror literature using ChatGPT?","Question",{"text":63,"@type":64},"It uses a GPT-4-based ChatGPT approach with a curated prompt containing specialized literature references to steer the generated text toward Lovecraft-like style and themes.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What method is used to evaluate whether the generated text matches Lovecraft’s works?",{"text":68,"@type":64},"The study administers a survey to undergraduate students and applies statistical hypothesis testing to measure whether participants can distinguish generated text from genuine Lovecraft works.",{"name":70,"@type":61,"acceptedAnswer":71},"What do the study’s findings suggest about prompt engineering and model performance?",{"text":72,"@type":64},"Participants were unable to reliably differentiate between original Lovecraft works and model-generated text, indicating the effectiveness of GPT-4 and the prompt engineering techniques used.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},514980,1791411145,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":33,"preview_urls":147},1374402739827,"https://ap-avatar.wpscdn.com/avatar/14000c97e7351f1a627?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787885694763230660","arXiv :2305 .03429v1 [ cs .CL] 5 May 2023  \nSimulating H.P. Lovecraft horror literature with the ChatGPT large language model  \nEduardo C. Garrido-Merch􀀓an, Jos􀀓e Luis Arroyo-Barrig􀁿uete, Roberto  \nGozalo-Brihuela  \nUniversidad Ponti􀀌cia Comillas, Madrid, Spain [jlarroyo@icade.comillas.edu](jlarroyo@icade.comillas.edu) , [ecgarrido@icade.comillas.edu](ecgarrido@icade.comillas.edu) , [201905616@alu.icade.comillas.edu](201905616@alu.icade.comillas.edu)  \nAbstract. In this paper, we present a novel approach to simulating H.P.  \nLovecraft's horror literature using the ChatGPT large language model, speci􀀌cally the GPT-4 architecture. Our study aims to generate text that emulates Lovecraft's unique writing style and themes, while also examining the e􀀋ectiveness of prompt engineering techniques in guiding the model's output. To achieve this, we curated a prompt containing several specialized literature references and employed advanced prompt engineering methods. We conducted an empirical evaluation of the generated text by administering a survey to a sample of undergraduate students.  \nUtilizing statistical hypothesis testing, we assessed the students' ability to distinguish between genuine Lovecraft works and those generated by our model. Our 􀀌ndings demonstrate that the participants were unable to reliably di􀀋erentiate between the two, indicating the e􀀋ectiveness of the GPT-4 model and our prompt engineering techniques in emulating Lovecraft's literary style. In addition to presenting the GPT model's capabilities, this paper provides a comprehensive description of its underlying architecture and o􀀋ers a comparative analysis with related work that simulates other notable authors and philosophers, such as Dennett.  \nBy exploring the potential of large language models in the context of literary emulation, our study contributes to the body of research on the applications and limitations of these models in various creative domains.  \nKeywords: Large Language Models, Weird Fiction, H.P. Lovecraft  \n1 Introduction  \nThe advent of advanced arti􀀌cial intelligence models has revolutionized various domains, including creative writing [55] . While these models have raised ethical concerns [61], the human-centered arti􀀌cial intelligence (HCAI) perspective posits that using AI for creative writing is a best use for the tool: both licit and ethically sound [61] . This position is further supported by the potential of AI to augment human creativity and contribute positively to the realm of literature. In this paper, we explore the use of the ChatGPT large language model [15] for simulating H.P.  \nLovecraft's horror literature, an endeavor that is in line with the HCAI perspective.  \n2 Eduardo C. Garrido-Merch􀀓an et. al.  \nGenerative models for creative writing have been developed and re-􀀌ned over the years, with numerous studies investigating their potential for generating diverse, engaging, and contextually appropriate content [9,24,53] . Recent advancements in the 􀀌eld have led to the creation of more powerful models, such as ChatGPT-4, which can generate humanlike text based on a given prompt [38] . This evolution has expanded the possibilities for AI-generated literature and opened the door for simulating works from renowned authors, such as H.P. Lovecraft.  \nThe objectives of this paper are threefold: (1) to provide an accessible explanation of the technical details of the GPT model to the literature community, fostering a greater understanding of its capabilities and limitations; (2) to simulate Lovecraft's writing style by crafting a complex prompt with literature references for GPT-4; and (3) to conduct statistical hypothesis testing to determine whether the generated text is indistinguishable from original Lovecraft works for undergraduate students.  \nThe paper is organized as follows: First, in section 2, we delve into the Generative Pretrained Transformer models, detailing their architecture and functioning. Then, in section 3, we outli","cbCairub0QMTbGwn","https://ap.wps.com/l/cbCairub0QMTbGwn","pdf",438107,14,"English","# Introduction\n## Objectives and paper organization\n# Generative Pretrained Transformer models\n## Architecture and self-attention mechanism","[{\"question\":\"How does the paper simulate H.P. Lovecraft’s horror literature using ChatGPT?\",\"answer\":\"It uses a GPT-4-based ChatGPT approach with a curated prompt containing specialized literature references to steer the generated text toward Lovecraft-like style and themes.\"},{\"question\":\"What method is used to evaluate whether the generated text matches Lovecraft’s works?\",\"answer\":\"The study administers a survey to undergraduate students and applies statistical hypothesis testing to measure whether participants can distinguish generated text from genuine Lovecraft works.\"},{\"question\":\"What do the study’s findings suggest about prompt engineering and model performance?\",\"answer\":\"Participants were unable to reliably differentiate between original Lovecraft works and model-generated text, indicating the effectiveness of GPT-4 and the prompt engineering techniques used.\"}]","Simulating H.P. Lovecraft horror literature with ChatGPT 3 | PDF",1791304681,35,[148,152,156,160],{"page_no":22,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/595025d0d64cc7fa38bd9386f2be5373.webp",983,1272,{"page_no":26,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/9338b20613c5c01a2196b5cffad381b7.webp",982,1270,{"page_no":30,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/b20143063c9a24c391d39bbf79512a9a.webp",981,1269,{"page_no":33,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/744078286dd199b982e95aab84fa17cb.webp",980,1268]