[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-576608-105":59,"doc-detail-576608-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","human-ai-interaction-with-large-language-models-in-complex-information-tasks-prompt-engineering-strategies","Human-AI Interaction with Large Language Models in Complex Information Tasks - Prompt Engineering Strategies","","This article examines how humans interact with large language models (LLMs) and conversational agents when tackling complex information tasks. It surveys current research on using AI in non-linear workflows that require interpretation, organization, and synthesis. The work frames prompting as an interactive medium that supports iterative problem-solving, and it offers guidance on task decomposition, iterative refinement, specifying audience and context, and assigning roles or personas. The paper concludes with implications aimed at strengthening human-AI communication and prompt-related AI literacy.",{"@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/human-ai-interaction-with-large-language-models-in-complex-information-tasks-prompt-engineering-strategies/576608/",{"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/human-ai-interaction-with-large-language-models-in-complex-information-tasks-prompt-engineering-strategies/576608.png","ImageObject",300,407,{"name":92,"@type":93},"Logic","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How does prompting influence human-AI interaction with large language models?","Question",{"text":112,"@type":113},"The paper presents prompting as a medium that helps users iteratively address complex information tasks and improve the usefulness of generative AI responses.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What are the key prompt engineering strategies recommended in the paper?",{"text":117,"@type":113},"The recommendations include task decomposition, iterative refinement, identifying audience and context, and assigning role/persona to guide outputs.",{"name":119,"@type":110,"acceptedAnswer":120},"What challenges can arise for users in complex information tasks using chatbots?",{"text":121,"@type":113},"The paper highlights risks such as information loss, communication breakdown, and user dissatisfaction, including cognitive overload when processing and storing chatbot-generated information.","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},576608,1792210216,{"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":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"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":143,"read_time":144,"preview_page_count":19,"preview_urls":145},1099513958762,"https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253","Human-AI Interaction with Large Language Models in Complex Information Tasks: Prompt Engineering Strategies  \nKadir Karakaya  \nAbstract: This article explores human-AI interaction with large language models or conversational agents in complex information tasks with a focus on prompt engineering strategies. The paper reviews the current literature on the use of artificial intelligence (AI) for complex information tasks that are often nonlinear and entail interpretation, organization, and synthesis of information. Building on the role prompting plays in enhancing generative AI responses, the study frames prompt engineering as a medium with the potential to enable users to iteratively tackle complex information tasks. It provides recommendations for the use of key prompting strategies such as task decomposition, iterative refinement, identification of audience and context, and role/persona assignment. Considering the notable importance of prompting as a critical AI literacy, the paper ends with several implications that might be conducive to enhance the human-AI communication in generative AI context.  \nKeywords: Generative AI, human-AI interaction, large language models, prompt engineering, complex information tasks, AI literacy, prompting strategies  \nHighlights  \nWhat is already known about this topic:  \n• Large language models (LLMs) have considerably shifted the ways users interact with computers.  \n• LLMs are widely used in the context of information exploration in human-AI interaction. What this paper contributes:  \n• Prompt engineering techniques (e.g. , Chain-of-Thought prompting) enhances human-AI interaction  \n• Prompt engineering strategies allows more accurate and useful outputs in complex information tasks.  \nImplications for theory, practice and/or policy:  \n• The ability to craft effective prompts becomes a critical skill for both personal and work environments.  \n• Prompting techniques should be implemented in real-world scenarios.  \nIntroduction  \nNatural language is the most congruent medium of communication to human beings, manifesting so far itself mostly in in-person or computer-mediated communication. However, recent developments in natural language processing and machine learning have considerably shifted the way humans interact with computers. Human computer interaction has started relying heavily on natural language user interfaces in which interaction takes place primarily in strings of texts in natural language (Følstad & Brandtzæg, 2017) . A contemporary example of such interaction is visible in the recent chatbots – also known as conversational AI, conversational agents, digital assistants, AI assistants, or bots-powered by generative Artificial Intelligence (AI) such as ChatGPT and Gemini. The fundamental building block to recent chatbots has been fueled by Large Language Models (LLMs) trained on massive corpora of texts capable of performing new tasks in response to textual prompts or from a couple examples (Touvron et al. , 2023) .  \nA crucial feature of large language models is their ability to engage in natural conversations with human users in human-like fashion as they have been trained on human language and discourse. The exponentially increasing size of training data and the number of parameters allow LLMs to be adapted to various domains from education to healthcare and to customer service. A notable function of LLMs exhibited in well-known generative AI applications is that they can process a large amount of input and produces an output as a response. Because LLMs have been trained on massive human language data, the underlying transformer model predicts likely response and yields a response to the query by the user (for details see Jurafsky & Martin, 2021) . In this way, LLMs can hold a conversational thread in a natural conversation with a human user. As opposed to mainstream interaction patterns with computers in which users search for a keyword or look for a list of entries provided by","cbCaii2p1r6I2uHx","https://ap.wps.com/l/cbCaii2p1r6I2uHx","pdf",269504,"English","# What Is Known About This Topic\n# What This Paper Contributes\n# Implications for Theory, Practice and/or Policy\n# Introduction\n# Human-AI Interaction Through Natural Language Interfaces\n# LLMs as Conversational Agents and Response Predictors\n# Challenges in Complex Information Tasks","[{\"question\":\"How does prompting influence human-AI interaction with large language models?\",\"answer\":\"The paper presents prompting as a medium that helps users iteratively address complex information tasks and improve the usefulness of generative AI responses.\"},{\"question\":\"What are the key prompt engineering strategies recommended in the paper?\",\"answer\":\"The recommendations include task decomposition, iterative refinement, identifying audience and context, and assigning role/persona to guide outputs.\"},{\"question\":\"What challenges can arise for users in complex information tasks using chatbots?\",\"answer\":\"The paper highlights risks such as information loss, communication breakdown, and user dissatisfaction, including cognitive overload when processing and storing chatbot-generated information.\"}]","Human-AI Interaction with Large Language Models in Complex Information Tasks - Prompt Engineering Strategies | PDF",1792030097,23,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/ab88def6eef587e05f525040c6eaadf4.webp",983,1390,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/68920b5627bf8bdedd1c13dd9ba529ed.webp",982,1388,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/f6ceac8710df95a6ead62bc436f26385.webp",981,1387,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-18/2e44b8f3c934cc2c9c0bf8719c9af332.webp",980,1385]