[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-293265-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-293265-en":130},{"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","from-black-box-to-disposition-1-surveying-divergence-novelty-and-ethics-in-large-language-models","From Black Box to Disposition - 1 - Surveying Divergence, Novelty, and Ethics in Large Language Models","","This study investigates the dispositional tendencies of large language models (LLMs) by developing and validating a survey instrument tailored to their unique characteristics. Building on and addressing limits of applying human psychometric frameworks such as the Big Five, the work introduces three traits that target functional dispositions: convergent-divergent reasoning, novel-conventional problem solving, and ethical orientation. A co-designed forced-choice questionnaire is evaluated against open-ended behavioral tasks, showing moderate-to-strong alignment with observed tendencies and consistent virtue-ethics expression across models. The framework supports interpretability, prompt design, and theoretical progress on personality-like constructs.",{"@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/from-black-box-to-disposition-1-surveying-divergence-novelty-and-ethics-in-large-language-models/293265/",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/from-black-box-to-disposition-1-surveying-divergence-novelty-and-ethics-in-large-language-models/293265.png","ImageObject",300,407,{"name":42,"@type":43},"Stanley","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the study address about LLM personality assessment?","Question",{"text":63,"@type":64},"It addresses limitations in prior work that adapts human psychometric frameworks to LLMs, focusing on conceptual and methodological issues.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which three traits does the study introduce to capture LLM dispositions?",{"text":68,"@type":64},"The traits are convergent-divergent reasoning, novel-conventional problem solving, and ethical orientation.",{"name":70,"@type":61,"acceptedAnswer":71},"How is the survey instrument validated in the study?",{"text":72,"@type":64},"A forced-choice questionnaire is co-designed with multiple models, then its predictive validity is tested against open-ended behavioral tasks.","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},293265,1789661733,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144,"preview_page_count":4},2336477405376,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Saskatchewan Polytechnic  \nLarge Language Models, LLM Personality Assessment, AI Interpretability, Computational Psychometrics  \n November 4th, 2025  \n [https://doi.org/10.21203/rs.3.rs-7992691/v1](https://doi.org/10.21203/rs.3.rs-7992691/v1)  \n 􀁱 􀅏 This work is licensed under a Creative Commons Attribution 4.0 International License.  \nRead Full License  \n No competing interests reported.  \nFrom Black Box to Disposition: Surveying Divergence, Novelty, and Ethics in Large Language Models  \n1  \nFrom Black Box to Disposition: Surveying Divergence, Novelty, and Ethics in Large Language  \nModels  \nAbstract  \nThis study investigates the dispositional tendencies of large language models (LLMs) by developing and validating a survey instrument tailored to their unique characteristics. While prior research has adapted human psychometric frameworks such as the Big Five to LLMs, these approaches face conceptual and methodological limitations. To address this gap, this study introduced three traits (convergent-divergent reasoning, novel-conventional problem solving, and ethical orientation) that more directly capture the functional dispositions of LLMs.  \nA forced-choice questionnaire was co-designed with multiple models to assess these traits, and its predictive validity was tested against open-ended behavioral tasks. Results demonstrate that questionnaire responses align with observed tendencies, with moderate-to-strong correlations for divergent and novel reasoning, and consistent expression of virtue ethics across models. These findings suggest that LLMs exhibit measurable, context-dependent dispositions that can be systematically assessed. The proposed framework contributes to ongoing efforts to interpret model behavior, inform prompt design, and advance the theoretical discourse on personality-like constructs in artificial systems.  \nKeywords: Large Language Models, LLM Personality Assessment, AI  \nInterpretability, Computational Psychometrics  \n1 Introduction  \nAs the use of large language models (LLMs) becomes more popular, many researchers have begun studying the behavioral interactions between users and the models. In particular, there is a belief that LLMs may have personalities (Jiang et al. , 2023; Pan & Zeng, 2023; Serapio-Garc´ıa et al. , 2023; Sonlu, Bendiksen, Durupinar, & G¨ud¨ukbay, 2024) that influence these interactions. This work has focused on translating research methods that identify human personalities to LLMs (Jiang et al. , 2023) . Often this research draws on existing personality questionnaires such as the Big Five (Jiang et al. , 2023; Serapio-Garc´ıa et al. , 2023; Sorokovikova, Fedorova, Rezagholi, & Yamshchikov, 2024; Zheng, Wang, Hosio, Xu, & Lee, 2025) and Myers-Briggs Type Indicator (Pan & Zeng, 2023) .  \n2  \nA glaring challenge of this research is that LLMs are not human. It is questionable whether LLMs, or any non-living thing, can have a personality at all. Thus, for the purpose of this research, personality will be defined as consistent and predictable internal characteristics that inform behavior. Specifically, are there characteristics that consistently and predictably determine the language the LLM exhibits?  \nLLMs are conditional language models. They are trained to generate a sentence by predicting the probability of the next word based on patterns learned in their training data (Frank, 2023) . The concept of personality in this context aims to discover the probabilistic tendencies of the output of the model. This is of importance because LLMs are black boxes; not even their designers understand their reasoning (Amodei, 2025) . The model’s use of language and the inferences we can make based on the language could shed light into the black box.  \nThe contribution of this paper is the development of a questionnaire to identify three personality traits that are predictive of LLM output. These dimensions include: divergent-convergent thinking, novel-conventional problem solving, and ethical foundations.  ","cbCaibZqLtCPnX7D","https://ap.wps.com/l/cbCaibZqLtCPnX7D","pdf",304839,27,"English","# Abstract\n# 1 Introduction\n# 2 Related Work\n## 2.1 Language and Personality","[{\"question\":\"What problem does the study address about LLM personality assessment?\",\"answer\":\"It addresses limitations in prior work that adapts human psychometric frameworks to LLMs, focusing on conceptual and methodological issues.\"},{\"question\":\"Which three traits does the study introduce to capture LLM dispositions?\",\"answer\":\"The traits are convergent-divergent reasoning, novel-conventional problem solving, and ethical orientation.\"},{\"question\":\"How is the survey instrument validated in the study?\",\"answer\":\"A forced-choice questionnaire is co-designed with multiple models, then its predictive validity is tested against open-ended behavioral tasks.\"}]","From Black Box to Disposition - 1 - Surveying Divergence, Novelty, and Ethics in Large Language Models | PDF",68]