Publications-Theses
Article View/Open
Publication Export
-
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
題名 大型語言模型內外向性格對用戶選擇閉合與風險決策的影響
Impact of LLM Introversion and Extraversion on User Choice Closure and Risk-Based Decision-Making作者 張庭綺
Chang, Ting-Chi貢獻者 簡士鎰
Chien, Shih-Yi
張庭綺
Chang, Ting-Chi關鍵詞 大型語言模型 (LLM)
選擇閉合
風險決策
AI 輔助決策
Large Language Models (LLM)
Choice closure
Risk-based decision-making
AI-assisted decision-making日期 2025 上傳時間 4-Aug-2025 14:27:56 (UTC+8) 摘要 隨著大型語言模型（LLM）在決策輔助領域的應用愈發普及，其擬人化對話風格對使用者行為的影響受到學界與業界的高度關注。然而，迄今尚缺乏針對不同人格風格的 LLM 在多元風險情境下影響機制的系統性研究。本研究基於 Prompt Induction post Supervised Fine-Tuning（PISF）技術，將 Meta-Llama-3-8B-Instruct 微調為「內向型」與「外向型」兩種對話風格，並設計高風險（投資基金分配）與低風險（留學保險方案選擇）兩種情境，邀請 32 名受試者完成行為任務與問卷測量。研究聚焦於「選擇閉合」（choice closure）與「建議採納」兩大行為指標，並檢驗外向性、風險承受度、技術不安感與宜人性等個人特質的調節效應。結果發現：外向型 LLM 顯著提升使用者在投資情境下嘗試高風險資產的意願，並於保險情境中加速決策閉合；內向型 LLM 則穩健地引導受試者集中於中等風險選項；在高風險的投資環境中，兩種對話風格受高認知負荷的影響而不顯著，兩者對選擇閉合效果的差異趨於平緩。此外，選擇閉合與決策滿意度呈現高度正相關，且使用者個人特質顯著調節以上關係。本研究不僅驗證了 PISF 技術在 LLM 人格操控上的可行性，還從認知負荷與說服理論的視角，深度闡明了擬人化對話風格如何影響使用者決策過程，並提出在不同風險場景下選擇最適對話風格的設計原則。最終，本研究為金融與保險等高風險決策領域的 AI 支援系統開發提供了具體的實證依據與操作建議，並期待透過擴大樣本與多元任務場景的後續研究，進一步驗證人格化 LLM 的廣泛適用性與潛在機制。
As Large Language Models (LLMs) become increasingly prevalent in decision-making assistance, their anthropomorphic conversational styles’ impact on user behavior has attracted significant academic and industry attention. However, systematic research on how different LLM personality styles influence users across diverse risk contexts remains lacking. This study used Prompt Induction post Supervised Fine-Tuning (PISF) to fine-tune Meta-Llama-3-8B-Instruct into "introverted" and "extroverted" personality, testing 32 participants across high-risk (investment fund allocation) and low-risk (study abroad insurance) scenarios. Focusing on "choice closure" and "recommendation adoption" behaviors, results showed extroverted LLMs significantly enhanced users’ willingness to attempt high-risk assets in investment scenarios and achieve higher closure in insurance contexts, while introverted LLMs consistently guided participants toward moderate-risk options. In high-risk investment scenario, both personalities became non-significant due to high cognitive load, with differences in choice closure effects becoming attenuated. Choice closure showed strong positive correlation with decision satisfaction, with personal traits significantly moderating these relationships. This study validates PISF technology’s feasibility for LLM personality manipulation and elucidates how anthropomorphic conversational styles influence decision-making through cognitive load and persuasion theory perspectives. It provides design principles for optimal conversational style selection across risk scenarios and empirical evidence for developing AI support systems in financial domains.參考文獻 Adriatico, J. M., Cruz, A., Tiong, R. C., & Racho-Sabugo, C. R. (2022). An analysis on the impact of choice overload to consumer decision paralysis. Journal of Economics, Finance and Accounting Studies. Anagnostidis, S., & Bulian, J. (2024). How Susceptible are LLMs to Influence in Prompts? arXiv.Org, abs/2408.11865. Andrews, D. (2013). The Interplay of Information Diagnosticity and Need for Cognitive Closure in Determining Choice Confidence. Psychology & Marketing, 30, 749-764. Armantier, O., Foncel, J., & Treich, N. (2023). Insurance and portfolio decisions: Two sides of the same coin? Journal of Financial Economics, 148(3), 201–219. Beike DR, Wirth-Beaumont E (2005) Psychological closure as a memory phenomenon. Memory 13(6):574–593. Bell, David E. (1982), “Regret in Decision Making under Uncertainty,” Operations Research, 30 (5), 961–81. Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. Borman, H., Leontjeva, A., Pizzato, L., Jiang, M.K., & Jermyn, D. (2024). Do LLM Personas Dream of Bull Markets? Comparing Human and AI Investment Strategies Through the Lens of the Five-Factor Model. ArXiv, abs/2411.05801. Boroujeni, A.A., Roohani, A., & Hasanimanesh, A. (2015). The Impact of Extraversion and Introversion Personality Types on EFL Learners’ Writing Ability. Theory and Practice in Language Studies, 5, 212-218. Botti, S., & McGill, A. L. (2006). When Choosing Is Not Deciding: The Effect of Perceived Responsibility on Satisfaction. Journal of Consumer Research, 33(2), 211–219. Carmon, Ziv, Klaus Wertenbroch, and Marcel Zeelenberg (2003), “Option Attachment: When Deliberating Makes Choosing Feel Like Losing,” Journal of Consumer Research, 30 (1), 15–29. Caron, G., & Srivastava, S. (2022). Identifying and Manipulating the Personality Traits of Language Models. Cerekovic, A., Aran, O., & Gatica-Perez, D. (2017). Rapport with virtual agents: What do human social cues and personality explain? IEEE Transactions on Affective Computing, 8(3), 382–395. Che, J., Sun, H., Xiao, C., & Li, A. (2019). Why information overload damages decisions? An explanation based on limited cognitive resources. Advances in Psychological Science, 27(10), 1758-1768. Chen, O., Paas, F., & Sweller, J. (2023). A Cognitive Load Theory Approach to Defining and Measuring Task Complexity Through Element Interactivity. Educational Psychology Review, 35(2). Chen, Y., Wen, Z., Fan, G., Chen, Z., Wu, W., Liu, D., Li, Z., Liu, B., & Xiao, Y. (2023). MAPO: Boosting large language model performance with model-adaptive prompt optimization. Findings of the Association for Computational Linguistics: EMNLP 2023, 3279–3304. Chen, Y., Wu, Z., Guo, J., Huang, S., & Dai, X. (2024). Extraversion or Introversion? Controlling The Personality of Your Large Language Models (arXiv:2406.04583). arXiv. Chiarulli, P., & Hebert, R.S. (2016). Premature diagnostic closure in palliative medicine. BMJ Supportive & Palliative Care, 6, 151 - 152. Cui, J., Lv, L., Wen, J., Wang, R., Tang, J., Tian, Y., & Yuan, L. (2023). Machine Mindset: An MBTI Exploration of Large Language Models (arXiv:2312.12999). De Angeli, A., Johnson, G. I., & Coventry, L. (2001). The unfriendly user: exploring social reactions to chatterbots. In Proceedings of the international conference on affective human factors design, london (pp. 467–474). London, UK: Asean Academic Press. De Vries, R. A. J., Truong, K. P., Zaga, C., Li, J., & Evers, V. (2017). A word of advice: How to tailor motivational text messages based on behavior change theory to personality and gender. Personal and Ubiquitous Computing, 21(4), 675–687. Desmond, M., Ashktorab, Z., Pan, Q., Dugan, C., & Johnson, J. M. (2024). EvaluLLM: LLM assisted evaluation of generative outputs. Companion Proceedings of the 29th International Conference on Intelligent User Interfaces, 30–32. Eigner, E., & Händler, T. (2024). Determinants of LLM-assisted Decision-Making. Fu, T., Conde, J., Mart’inez, G., Grandury, M., & Reviriego, P. (2025). Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong. Greenleaf, Eric A & Lehmann, Donald R, 1995. Reasons for Substantial Delay in Consumer Decision Making," Journal of Consumer Research, Journal of Consumer Research Inc., vol. 22(2), pages 186-199, September. Gu, Y., Botti, S., & Faro, D. (2013). Turning the page: The impact of choice closure on satisfaction. Journal of Consumer Research, 40(2), 268–283. Gu, Y., Botti, S., & Faro, D. (2018). Seeking and Avoiding Choice Closure to Enhance Outcome Satisfaction. Journal of Consumer Research, 45(4), 792–809. Hart, W., Adams, J. M., Burton, K. A., Shreves, W. B., & Hamilton, J. C. (2012). Shaping reality vs. hiding from reality: Reconsidering the effects of trait need for closure on information search. Journal of Research in Personality, 46(5), 489–496. Haynes, G.A. (2009). Testing the boundaries of the choice overload phenomenon: The effect of number of options and time pressure on decision difficulty and satisfaction. Psychology & Marketing, 26, 204-212. Hsee, Christopher K., George F. Loewenstein, Sally Blount, and Max H. Bazerman (1999), “Preference Reversals between Joint and Separate Evaluation of Options: A Review and Theoretical Analysis,” Psychological Bulletin, 125 (5), 576–90. Hu, Y., Wang, X., Yao, W., Lu, Y., Zhang, D., Foroosh, H., Yu, D., & Liu, F. (2024). DeFine: Enhancing LLM Decision-Making with Factor Profiles and Analogical Reasoning. Huang, J., Wang, W., Lam, M. H., Li, E. J., Jiao, W., & Lyu, M. R. (2023). Revisiting the Reliability of Psychological Scales on Large Language Models. Imasaka, Y., & Joho, H. (2024). Effect of LLM’s personality traits on query generation. In Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP 2024) (pp. 249–258). Association for Computing Machinery. Jaśko, K., Czernatowicz-Kukuczka, A., Kossowska, M., & Czarna, A. Z. (2015). Individual differences in response to uncertainty and decision making: The role of behavioral inhibition system and need for closure. Motivation and Emotion, 39(4), 541–552. Jiang, G., Xu, M., Zhu, S.-C., Han, W., Zhang, C., & Zhu, Y. (2023). Evaluating and Inducing Personality in Pre-trained Language Models. Advances in Neural Information Processing Systems. John, O. P. (1991). The big five inventory—versions 4a and 54. (No Title). John, O. P., & Srivastava, S. (1999). The Big-Five trait taxonomy: History, measurement, and theoretical perspectives. In L. A. Pervin & O. P. John (Eds.), Handbook of personality: Theory and research (Vol. 2, pp. 102–138). New York: Guilford Press. Karine, K., & Marlin, B.M. (2025). Combining LLM decision and RL action selection to improve RL policy for adaptive interventions. ArXiv, abs/2501.06980. Kayaoğlu, M.N. (2013). Impact of Extraversion and introversion on language-learning behaviors. Social Behavior and Personality, 41, 819-826. Kim, J., Kim, J.H., Kim, C., & Park, J. (2023). Decisions with ChatGPT: Reexamining choice overload in ChatGPT recommendations. Journal of Retailing and Consumer Services. Kim, J., Kovach, M., Lee, K., Shin, E., & Tzavellas, H. (2024). Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice. Kitchen, P. J., Kerr, G., Schultz, D. E., McColl, R., & Pals, H. (2014). The elaboration likelihood model: Review, critique and research agenda. European Journal of Marketing, 48(11/12), 2033–2050. Klein, G. (2008). Naturalistic Decision Making. Human Factors, 50(3), 456-460. Kroczek, L.O., May, A., Hettenkofer, S., Ruider, A., Ludwig, B., & Mühlberger, A. (2024). The influence of persona and conversational task on social interactions with a LLM-controlled embodied conversational agent. Kumar, A., Raghunathan, A., Jones, R., Ma, T., & Liang, P. (2022). Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv. Kumar, B., Kanna, B., & Kumar, S. (2011). The pitfalls of premature closure: Clinical decision-making in a case of aortic dissection. Case Reports, 2011, bcr0820114594. Lee, Y., Chen, A. N. K., & Wang, W. (2025). Push it across the finish line: Designing online interfaces to induce choice closure at the postdecision prepurchase stage. Information Systems Research. Advance online publication. Lin, J.-S. C., & Hsieh, P.-ling (2006). The role of technology readiness in customers’ perception and adoption of self-service technologies. International Journal of Service Industry Management, 17(5), 497–517. Liu, O., Fu, D., Yogatama, D., & Neiswanger, W. (2024). DeLLMa: Decision Making Under Uncertainty with Large Language Models (arXiv:2402.02392). Long, D., & Magerko, B. (2020). What is AI literacy? Competencies and design considerations. In Proceedings of the 2020 CHI conference on human factors in computing systems (pp. 1–16). Lu, Y., Hu, Y., Foroosh, H., Jin, W., & Liu, F. (2024). STRUX: An LLM for Decision-Making with Structured Explanations. Luo J, Ba S, Zhang H (2012) The effectiveness of online shopping characteristics and well-designed websites on satisfaction. MIS Quart. 36(4):1131–1144. Majumder, M., & Ghosh, S. (2013). Decision Making Methodology. Mao, S., Wang, X., Wang, M., Jiang, Y., Xie, P., Huang, F., & Zhang, N. (2024). Editing Personality For LLMs. Morgan, J. P. (2023). Morgan Asset Management Client Risk Profile Assessment Form. https://am.jpmorgan.com/content/dam/jpm-am-aem/asiapacific/tw/zh/supplemental/jf-kyc-nat.pdf Moser, C., Phelan, C., Resnick, P., Schoenebeck, S.Y., & Reinecke, K. (2017). No Such Thing as Too Much Chocolate: Evidence Against Choice Overload in E-Commerce. Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Mukherjee, S., & De, S. (2018). When Are Investors Rational? Journal of Behavioral Finance, 20(1), 1–18. Myers, I. B. (1962). The Myers-Briggs Type Indicator: Manual (1962). Consulting Psychologists Press. Neth, H., Engelmann, N., & Mayrhofer, R. (2014). Foraging for Alternatives: Ecological Rationality in Keeping Options Viable. Cognitive Science, 36(36). Ning, Z. E., Villas-Boas, J. M., & Yao, Y. (Jesse). (2025). Search Fatigue, Choice Deferral, and Closure. Marketing Science. Oehler, A., & Wedlich, F. (2018). The Relationship of Extraversion and Neuroticism with Risk Attitude, Risk Perception, and Return Expectations. Journal of Neuroscience, Psychology, and Economics, 11, 63–92. Oviedo-Trespalacios, O., Peden, A. E., Cole-Hunter, T., Costantini, A., Haghani, M., Rod, J. E., Kelly, S., Torkamaan, H., Tariq, A., Newton, J. D. A., Gallagher, T., Steinert, S., Filtness, A., & Reniers, G. (2023). The risks of using ChatGPT to obtain common safety-related information and advice. Pan, C., & Statman, M. (2012). Investor Personality in Investor Questionnaires. Behavioral & Experimental Finance (Editor’s Choice) eJournal. Parasuraman, A., & Colby, C. L. (2014). An Updated and Streamlined Technology Readiness Index: TRI 2.0. Journal of Service Research, 18(1), 59-74. Pescetelli, N., & Yeung, N. (2021). The role of decision confidence in advice-taking and trust formation. Journal of experimental psychology. General, 150(3), 507–526. Petty, Richard & Cacioppo, John. (1986). The Elaboration Likelihood Model of Persuasion. Advances in Experimental Social Psychology. 19. 123-205. Ramani, G., Karande, S., Santhosh, V., & Bhatia, Y. (2024). Persuasion Games using Large Language Models. Rockwell, T.H., & Burner, L.R. (1968). Information Seeking in Risk Acceptance. Rogers, K., Webber, R. J. A., Gorostiaga Zubizarreta, G., Melo Cruz, A., Chen, S., Arkin, R. C., Borenstein, J., & Wagner, A. R. (2024). What Should a Robot Do? Comparing Human and Large Language Model Recommendations for Robot Deception. Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 906–910. Sahoo, P., Singh, A. K., Saha, S., Jain, V., Mondal, S., & Chadha, A. (2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv. Scheibehenne, B., Greifeneder, R., & Todd, P. M. (2010). Can there ever be too many options? A meta-analytic review of choice overload. Journal of Consumer Research, 37(3), 409–425. Shum, H.-y., He, X.-d., & Li, D. (2018). From Eliza to XiaoIce: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering. Song, X., Gupta, A., Mohebbizadeh, K., Hu, S., & Singh, A. (2023). Have Large Language Models Developed a Personality? Applicability of Self-Assessment Tests in Measuring Personality in LLMs. Sweller, J. (2011). Cognitive load theory. In J. P. Mestre & B. H. Ross (Eds.), The psychology of learning and motivation: Cognition in education (pp. 37–76). Elsevier Academic Press. Teodorescu, K., & Erev, I. (2014). On the Decision to Explore New Alternatives: The Coexistence of Under‐ and Over‐exploration. Journal of Behavioral Decision Making, 27(2), 109–123. Vestewig, R.E. (1977). Extraversion and risk preference in portfolio theory. The Journal of psychology, 97 2d Half, 237-45. Wan, X., Sun, R., Dai, H., Arık, S. Ö., & Pfister, T. (2023). Better zero-shot reasoning with self-adaptive prompting. Findings of the Association for Computational Linguistics: ACL 2023. Wan, Y., Menon, S., & Ramaprasad, A. (2003). How It Happens: A Conceptual Explanation of Choice Overload in Online Decision-Making by Individuals. Americas Conference on Information Systems. Wang, Y., Tree, J. E. F., Walker, M., & Neff, M. (2016). Assessing the impact of hand motion on virtual character personality. ACM Transactions on Applied Perception (TAP), 13(2), 1-23. Weigold, M.F., & Schlenker, B.R. (1991). Accountability and Risk Taking. Personality and Social Psychology Bulletin, 17, 25 - 29. Wester, J., De Jong, S., Pohl, H., & Van Berkel, N. (2024). Exploring people’s perceptions of LLM-generated advice. Computers in Human Behavior: Artificial Humans, 2(2), 100072. Wong, A.S., & Carducci, B.J. (2013). Does Personality Affect Personal Financial Risk Tolerance Behavior. The IUP Journal of Applied Finance, 19, 5-18. Yan, D., & Chen, L. (2023). The influence of personality traits on user interaction with recommendation interfaces. ACM Transactions on Interactive Intelligent Systems, 13(1), 39. Yang, J. C., Dailisan, D., Korecki, M., Hausladen, C. I., & Helbing, D. (2024). LLM Voting: Human Choices and AI Collective Decision Making. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7, 1696–1708. Zeelenberg, Marcel (1999), “Anticipated Regret, Expected Feedback, and Behavioral Decision Making,” Journal of Behavioral Decision Making, 12 (2), 93–106. Zongrone, B.M., Derrick, D.C., & Ligon, G.S. (2015). Individual Differences that Predict Interactions in Mixed-Initiative Teams. Hawaii International Conference on System Sciences, 610-618. Zoria, О., Zoria, S., & Kapaieva, L. (2022). Theoretical and methodological principles of investment risks insurance in their management system. 69. 描述 碩士
國立政治大學
資訊管理學系
112356041資料來源 http://thesis.lib.nccu.edu.tw/record/#G0112356041 資料類型 thesis dc.contributor.advisor 簡士鎰 zh_TW dc.contributor.advisor Chien, Shih-Yi en_US dc.contributor.author (Authors) 張庭綺 zh_TW dc.contributor.author (Authors) Chang, Ting-Chi en_US dc.creator (作者) 張庭綺 zh_TW dc.creator (作者) Chang, Ting-Chi en_US dc.date (日期) 2025 en_US dc.date.accessioned 4-Aug-2025 14:27:56 (UTC+8) - dc.date.available 4-Aug-2025 14:27:56 (UTC+8) - dc.date.issued (上傳時間) 4-Aug-2025 14:27:56 (UTC+8) - dc.identifier (Other Identifiers) G0112356041 en_US dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/158580 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊管理學系 zh_TW dc.description (描述) 112356041 zh_TW dc.description.abstract (摘要) 隨著大型語言模型（LLM）在決策輔助領域的應用愈發普及，其擬人化對話風格對使用者行為的影響受到學界與業界的高度關注。然而，迄今尚缺乏針對不同人格風格的 LLM 在多元風險情境下影響機制的系統性研究。本研究基於 Prompt Induction post Supervised Fine-Tuning（PISF）技術，將 Meta-Llama-3-8B-Instruct 微調為「內向型」與「外向型」兩種對話風格，並設計高風險（投資基金分配）與低風險（留學保險方案選擇）兩種情境，邀請 32 名受試者完成行為任務與問卷測量。研究聚焦於「選擇閉合」（choice closure）與「建議採納」兩大行為指標，並檢驗外向性、風險承受度、技術不安感與宜人性等個人特質的調節效應。結果發現：外向型 LLM 顯著提升使用者在投資情境下嘗試高風險資產的意願，並於保險情境中加速決策閉合；內向型 LLM 則穩健地引導受試者集中於中等風險選項；在高風險的投資環境中，兩種對話風格受高認知負荷的影響而不顯著，兩者對選擇閉合效果的差異趨於平緩。此外，選擇閉合與決策滿意度呈現高度正相關，且使用者個人特質顯著調節以上關係。本研究不僅驗證了 PISF 技術在 LLM 人格操控上的可行性，還從認知負荷與說服理論的視角，深度闡明了擬人化對話風格如何影響使用者決策過程，並提出在不同風險場景下選擇最適對話風格的設計原則。最終，本研究為金融與保險等高風險決策領域的 AI 支援系統開發提供了具體的實證依據與操作建議，並期待透過擴大樣本與多元任務場景的後續研究，進一步驗證人格化 LLM 的廣泛適用性與潛在機制。 zh_TW dc.description.abstract (摘要) As Large Language Models (LLMs) become increasingly prevalent in decision-making assistance, their anthropomorphic conversational styles’ impact on user behavior has attracted significant academic and industry attention. However, systematic research on how different LLM personality styles influence users across diverse risk contexts remains lacking. This study used Prompt Induction post Supervised Fine-Tuning (PISF) to fine-tune Meta-Llama-3-8B-Instruct into "introverted" and "extroverted" personality, testing 32 participants across high-risk (investment fund allocation) and low-risk (study abroad insurance) scenarios. Focusing on "choice closure" and "recommendation adoption" behaviors, results showed extroverted LLMs significantly enhanced users’ willingness to attempt high-risk assets in investment scenarios and achieve higher closure in insurance contexts, while introverted LLMs consistently guided participants toward moderate-risk options. In high-risk investment scenario, both personalities became non-significant due to high cognitive load, with differences in choice closure effects becoming attenuated. Choice closure showed strong positive correlation with decision satisfaction, with personal traits significantly moderating these relationships. This study validates PISF technology’s feasibility for LLM personality manipulation and elucidates how anthropomorphic conversational styles influence decision-making through cognitive load and persuasion theory perspectives. It provides design principles for optimal conversational style selection across risk scenarios and empirical evidence for developing AI support systems in financial domains. en_US dc.description.tableofcontents 摘要 2 ABSTRACT 3 TABLE OF CONTENTS 4 TABLES 7 FIGURES 10 CHAPTER 1 INTRODUCTION 11 CHAPTER 2 RELATED WORK 17 2.1 Shaping LLM Behavior: Introverted and Extroverted Traits 17 2.1.1 Behavioral Characteristics of Introverted and Extroverted LLMs 17 2.1.2 Comparison of LLM Personality Adjustment Techniques 18 2.1.3 Justification for Choosing PISF as the Personality Adjustment Method 21 2.2 LLM Personality Traits and Choice Closure 23 2.2.1 The Concept of Choice Closure 23 2.2.2 How LLM Intervention Influences Choice Closure 24 2.2.3 The Relationship Between Choice Closure and Decision Satisfaction 28 2.3 The Influence of Choice Closure Timing 29 2.4 Moderating Role of Individual Characteristics 30 2.4.1 Moderating Effect of Agreeableness and Extraversion on LLM Influence 31 2.4.2 Moderating Effect of Technological Insecurity on LLM Influence 34 2.4.3 Moderating Effect of Investment Risk Tolerance on Choice Closure 35 CHAPTER 3 LLM PERSONALITY SETUP AND PILOT EVALUATION 37 3.1 LLM Personality Adjustment Implementation 37 3.2 Consistency Evaluation of LLM Personality Manipulation 40 3.2.1 BFI Test Result 40 3.2.2 Pilot Test 42 CHAPTER 4 MAIN STUDY DESIGN 49 4.1 Overview 49 4.2 Experimental Procedure 51 4.3 Justification for Experimental Design 57 4.3.2 Impact of LLM Personality on Risk-Taking Behavior 58 4.3.3 Role of Individual Differences in Decision-Making 59 4.3.4 The Contributions and Applications of the Research Design 60 CHAPTER 5 RESULTS 61 5.1 Pilot Test Results 61 5.1.1 Investment Context Pilot Study 61 5.1.2 Insurance Context Pilot Study 65 5.2 Participant Demographics 68 5.2.1 Sample Characteristics 68 5.2.2 Agreeableness, Extraversion, Technological Insecurity and Risk Tolerance Distributions 69 5.3 Manipulation Check Results 71 5.3.1 Personality Manipulation Effectiveness in the Investment Context 71 5.3.2 Personality Manipulation Effectiveness in the Insurance Context 73 5.3.3 Comparison of Extraversion Scores between Investment and Insurance Contexts 75 5.4 Hypothesis Verification 76 5.4.1 H1: High‐Risk Investment Choices 76 5.4.2 H2: Moderating Effect on Choice Closure 87 5.4.3 H3: Relationship between Choice Closure and Decision Satisfaction 95 5.4.4 H4: Differences in Decision Time, Query Frequency, and Allocation Conservatism 97 5.4.5 H5 (a) and H5 (b): Individual Differences – Agreeableness 99 5.4.6 H5 (c) and H5 (d): Individual Differences – Extraversion 111 5.4.7 H6: Individual Differences – Technological Insecurity 120 5.4.8 H7: Individual Differences – Risk Tolerance 130 CHAPTER 6 GENERAL DISCUSSION 133 6.1 Theoretical Insights 134 6.1.1 Correlation Between Suggestion Acceptance and Choice Closure 134 6.1.2 Different Types of Choice Closure Achievement 136 6.2 Managerial Implications 138 6.3 Limitations and Future Research 140 REFERENCE 142 APPENDIX A PROMPT USED FOR ADJUSTING LLM PERSONALITY AFTER FINE-TUNING 148 APPENDIX B TRAINING PARAMETERS FOR SUPERVISED FINE-TUNING 158 APPENDIX C EXAMPLE INTERACTION OF INTROVERTED AND EXTROVERTED LLMS IN A GENERAL CONTEXT 159 APPENDIX D QUESTIONNAIRE USED IN PILOT TESTING 161 APPENDIX E CHOICE CLOSURE AND DECISION SATISFACTION SCALE 163 APPENDIX F PRE-TEST QUESTIONNAIRE 165 APPENDIX G EXPERIMENTAL SCENARIO AND PRODUCT TABLE 166 APPENDIX H USER INTERACTION FLOW 173 zh_TW dc.format.extent 3679713 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0112356041 en_US dc.subject (關鍵詞) 大型語言模型 (LLM) zh_TW dc.subject (關鍵詞) 選擇閉合 zh_TW dc.subject (關鍵詞) 風險決策 zh_TW dc.subject (關鍵詞) AI 輔助決策 zh_TW dc.subject (關鍵詞) Large Language Models (LLM) en_US dc.subject (關鍵詞) Choice closure en_US dc.subject (關鍵詞) Risk-based decision-making en_US dc.subject (關鍵詞) AI-assisted decision-making en_US dc.title (題名) 大型語言模型內外向性格對用戶選擇閉合與風險決策的影響 zh_TW dc.title (題名) Impact of LLM Introversion and Extraversion on User Choice Closure and Risk-Based Decision-Making en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Adriatico, J. M., Cruz, A., Tiong, R. C., & Racho-Sabugo, C. R. (2022). An analysis on the impact of choice overload to consumer decision paralysis. Journal of Economics, Finance and Accounting Studies. Anagnostidis, S., & Bulian, J. (2024). How Susceptible are LLMs to Influence in Prompts? arXiv.Org, abs/2408.11865. Andrews, D. (2013). The Interplay of Information Diagnosticity and Need for Cognitive Closure in Determining Choice Confidence. Psychology & Marketing, 30, 749-764. Armantier, O., Foncel, J., & Treich, N. (2023). Insurance and portfolio decisions: Two sides of the same coin? Journal of Financial Economics, 148(3), 201–219. Beike DR, Wirth-Beaumont E (2005) Psychological closure as a memory phenomenon. Memory 13(6):574–593. Bell, David E. (1982), “Regret in Decision Making under Uncertainty,” Operations Research, 30 (5), 961–81. Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. Borman, H., Leontjeva, A., Pizzato, L., Jiang, M.K., & Jermyn, D. (2024). Do LLM Personas Dream of Bull Markets? Comparing Human and AI Investment Strategies Through the Lens of the Five-Factor Model. ArXiv, abs/2411.05801. Boroujeni, A.A., Roohani, A., & Hasanimanesh, A. (2015). The Impact of Extraversion and Introversion Personality Types on EFL Learners’ Writing Ability. Theory and Practice in Language Studies, 5, 212-218. Botti, S., & McGill, A. L. (2006). When Choosing Is Not Deciding: The Effect of Perceived Responsibility on Satisfaction. Journal of Consumer Research, 33(2), 211–219. Carmon, Ziv, Klaus Wertenbroch, and Marcel Zeelenberg (2003), “Option Attachment: When Deliberating Makes Choosing Feel Like Losing,” Journal of Consumer Research, 30 (1), 15–29. Caron, G., & Srivastava, S. (2022). Identifying and Manipulating the Personality Traits of Language Models. Cerekovic, A., Aran, O., & Gatica-Perez, D. (2017). Rapport with virtual agents: What do human social cues and personality explain? IEEE Transactions on Affective Computing, 8(3), 382–395. Che, J., Sun, H., Xiao, C., & Li, A. (2019). Why information overload damages decisions? An explanation based on limited cognitive resources. Advances in Psychological Science, 27(10), 1758-1768. Chen, O., Paas, F., & Sweller, J. (2023). A Cognitive Load Theory Approach to Defining and Measuring Task Complexity Through Element Interactivity. Educational Psychology Review, 35(2). Chen, Y., Wen, Z., Fan, G., Chen, Z., Wu, W., Liu, D., Li, Z., Liu, B., & Xiao, Y. (2023). MAPO: Boosting large language model performance with model-adaptive prompt optimization. Findings of the Association for Computational Linguistics: EMNLP 2023, 3279–3304. Chen, Y., Wu, Z., Guo, J., Huang, S., & Dai, X. (2024). Extraversion or Introversion? Controlling The Personality of Your Large Language Models (arXiv:2406.04583). arXiv. Chiarulli, P., & Hebert, R.S. (2016). Premature diagnostic closure in palliative medicine. BMJ Supportive & Palliative Care, 6, 151 - 152. Cui, J., Lv, L., Wen, J., Wang, R., Tang, J., Tian, Y., & Yuan, L. (2023). Machine Mindset: An MBTI Exploration of Large Language Models (arXiv:2312.12999). De Angeli, A., Johnson, G. I., & Coventry, L. (2001). The unfriendly user: exploring social reactions to chatterbots. In Proceedings of the international conference on affective human factors design, london (pp. 467–474). London, UK: Asean Academic Press. De Vries, R. A. J., Truong, K. P., Zaga, C., Li, J., & Evers, V. (2017). A word of advice: How to tailor motivational text messages based on behavior change theory to personality and gender. Personal and Ubiquitous Computing, 21(4), 675–687. Desmond, M., Ashktorab, Z., Pan, Q., Dugan, C., & Johnson, J. M. (2024). EvaluLLM: LLM assisted evaluation of generative outputs. Companion Proceedings of the 29th International Conference on Intelligent User Interfaces, 30–32. Eigner, E., & Händler, T. (2024). Determinants of LLM-assisted Decision-Making. Fu, T., Conde, J., Mart’inez, G., Grandury, M., & Reviriego, P. (2025). Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong. Greenleaf, Eric A & Lehmann, Donald R, 1995. Reasons for Substantial Delay in Consumer Decision Making," Journal of Consumer Research, Journal of Consumer Research Inc., vol. 22(2), pages 186-199, September. Gu, Y., Botti, S., & Faro, D. (2013). Turning the page: The impact of choice closure on satisfaction. Journal of Consumer Research, 40(2), 268–283. Gu, Y., Botti, S., & Faro, D. (2018). Seeking and Avoiding Choice Closure to Enhance Outcome Satisfaction. Journal of Consumer Research, 45(4), 792–809. Hart, W., Adams, J. M., Burton, K. A., Shreves, W. B., & Hamilton, J. C. (2012). Shaping reality vs. hiding from reality: Reconsidering the effects of trait need for closure on information search. Journal of Research in Personality, 46(5), 489–496. Haynes, G.A. (2009). Testing the boundaries of the choice overload phenomenon: The effect of number of options and time pressure on decision difficulty and satisfaction. Psychology & Marketing, 26, 204-212. Hsee, Christopher K., George F. Loewenstein, Sally Blount, and Max H. Bazerman (1999), “Preference Reversals between Joint and Separate Evaluation of Options: A Review and Theoretical Analysis,” Psychological Bulletin, 125 (5), 576–90. Hu, Y., Wang, X., Yao, W., Lu, Y., Zhang, D., Foroosh, H., Yu, D., & Liu, F. (2024). DeFine: Enhancing LLM Decision-Making with Factor Profiles and Analogical Reasoning. Huang, J., Wang, W., Lam, M. H., Li, E. J., Jiao, W., & Lyu, M. R. (2023). Revisiting the Reliability of Psychological Scales on Large Language Models. Imasaka, Y., & Joho, H. (2024). Effect of LLM’s personality traits on query generation. In Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP 2024) (pp. 249–258). Association for Computing Machinery. Jaśko, K., Czernatowicz-Kukuczka, A., Kossowska, M., & Czarna, A. Z. (2015). Individual differences in response to uncertainty and decision making: The role of behavioral inhibition system and need for closure. Motivation and Emotion, 39(4), 541–552. Jiang, G., Xu, M., Zhu, S.-C., Han, W., Zhang, C., & Zhu, Y. (2023). Evaluating and Inducing Personality in Pre-trained Language Models. Advances in Neural Information Processing Systems. John, O. P. (1991). The big five inventory—versions 4a and 54. (No Title). John, O. P., & Srivastava, S. (1999). The Big-Five trait taxonomy: History, measurement, and theoretical perspectives. In L. A. Pervin & O. P. John (Eds.), Handbook of personality: Theory and research (Vol. 2, pp. 102–138). New York: Guilford Press. Karine, K., & Marlin, B.M. (2025). Combining LLM decision and RL action selection to improve RL policy for adaptive interventions. ArXiv, abs/2501.06980. Kayaoğlu, M.N. (2013). Impact of Extraversion and introversion on language-learning behaviors. Social Behavior and Personality, 41, 819-826. Kim, J., Kim, J.H., Kim, C., & Park, J. (2023). Decisions with ChatGPT: Reexamining choice overload in ChatGPT recommendations. Journal of Retailing and Consumer Services. Kim, J., Kovach, M., Lee, K., Shin, E., & Tzavellas, H. (2024). Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice. Kitchen, P. J., Kerr, G., Schultz, D. E., McColl, R., & Pals, H. (2014). The elaboration likelihood model: Review, critique and research agenda. European Journal of Marketing, 48(11/12), 2033–2050. Klein, G. (2008). Naturalistic Decision Making. Human Factors, 50(3), 456-460. Kroczek, L.O., May, A., Hettenkofer, S., Ruider, A., Ludwig, B., & Mühlberger, A. (2024). The influence of persona and conversational task on social interactions with a LLM-controlled embodied conversational agent. Kumar, A., Raghunathan, A., Jones, R., Ma, T., & Liang, P. (2022). Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv. Kumar, B., Kanna, B., & Kumar, S. (2011). The pitfalls of premature closure: Clinical decision-making in a case of aortic dissection. Case Reports, 2011, bcr0820114594. Lee, Y., Chen, A. N. K., & Wang, W. (2025). Push it across the finish line: Designing online interfaces to induce choice closure at the postdecision prepurchase stage. Information Systems Research. Advance online publication. Lin, J.-S. C., & Hsieh, P.-ling (2006). The role of technology readiness in customers’ perception and adoption of self-service technologies. International Journal of Service Industry Management, 17(5), 497–517. Liu, O., Fu, D., Yogatama, D., & Neiswanger, W. (2024). DeLLMa: Decision Making Under Uncertainty with Large Language Models (arXiv:2402.02392). Long, D., & Magerko, B. (2020). What is AI literacy? Competencies and design considerations. In Proceedings of the 2020 CHI conference on human factors in computing systems (pp. 1–16). Lu, Y., Hu, Y., Foroosh, H., Jin, W., & Liu, F. (2024). STRUX: An LLM for Decision-Making with Structured Explanations. Luo J, Ba S, Zhang H (2012) The effectiveness of online shopping characteristics and well-designed websites on satisfaction. MIS Quart. 36(4):1131–1144. Majumder, M., & Ghosh, S. (2013). Decision Making Methodology. Mao, S., Wang, X., Wang, M., Jiang, Y., Xie, P., Huang, F., & Zhang, N. (2024). Editing Personality For LLMs. Morgan, J. P. (2023). Morgan Asset Management Client Risk Profile Assessment Form. https://am.jpmorgan.com/content/dam/jpm-am-aem/asiapacific/tw/zh/supplemental/jf-kyc-nat.pdf Moser, C., Phelan, C., Resnick, P., Schoenebeck, S.Y., & Reinecke, K. (2017). No Such Thing as Too Much Chocolate: Evidence Against Choice Overload in E-Commerce. Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Mukherjee, S., & De, S. (2018). When Are Investors Rational? Journal of Behavioral Finance, 20(1), 1–18. Myers, I. B. (1962). The Myers-Briggs Type Indicator: Manual (1962). Consulting Psychologists Press. Neth, H., Engelmann, N., & Mayrhofer, R. (2014). Foraging for Alternatives: Ecological Rationality in Keeping Options Viable. Cognitive Science, 36(36). Ning, Z. E., Villas-Boas, J. M., & Yao, Y. (Jesse). (2025). Search Fatigue, Choice Deferral, and Closure. Marketing Science. Oehler, A., & Wedlich, F. (2018). The Relationship of Extraversion and Neuroticism with Risk Attitude, Risk Perception, and Return Expectations. Journal of Neuroscience, Psychology, and Economics, 11, 63–92. Oviedo-Trespalacios, O., Peden, A. E., Cole-Hunter, T., Costantini, A., Haghani, M., Rod, J. E., Kelly, S., Torkamaan, H., Tariq, A., Newton, J. D. A., Gallagher, T., Steinert, S., Filtness, A., & Reniers, G. (2023). The risks of using ChatGPT to obtain common safety-related information and advice. Pan, C., & Statman, M. (2012). Investor Personality in Investor Questionnaires. Behavioral & Experimental Finance (Editor’s Choice) eJournal. Parasuraman, A., & Colby, C. L. (2014). An Updated and Streamlined Technology Readiness Index: TRI 2.0. Journal of Service Research, 18(1), 59-74. Pescetelli, N., & Yeung, N. (2021). The role of decision confidence in advice-taking and trust formation. Journal of experimental psychology. General, 150(3), 507–526. Petty, Richard & Cacioppo, John. (1986). The Elaboration Likelihood Model of Persuasion. Advances in Experimental Social Psychology. 19. 123-205. Ramani, G., Karande, S., Santhosh, V., & Bhatia, Y. (2024). Persuasion Games using Large Language Models. Rockwell, T.H., & Burner, L.R. (1968). Information Seeking in Risk Acceptance. Rogers, K., Webber, R. J. A., Gorostiaga Zubizarreta, G., Melo Cruz, A., Chen, S., Arkin, R. C., Borenstein, J., & Wagner, A. R. (2024). What Should a Robot Do? Comparing Human and Large Language Model Recommendations for Robot Deception. Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 906–910. Sahoo, P., Singh, A. K., Saha, S., Jain, V., Mondal, S., & Chadha, A. (2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv. Scheibehenne, B., Greifeneder, R., & Todd, P. M. (2010). Can there ever be too many options? A meta-analytic review of choice overload. Journal of Consumer Research, 37(3), 409–425. Shum, H.-y., He, X.-d., & Li, D. (2018). From Eliza to XiaoIce: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering. Song, X., Gupta, A., Mohebbizadeh, K., Hu, S., & Singh, A. (2023). Have Large Language Models Developed a Personality? Applicability of Self-Assessment Tests in Measuring Personality in LLMs. Sweller, J. (2011). Cognitive load theory. In J. P. Mestre & B. H. Ross (Eds.), The psychology of learning and motivation: Cognition in education (pp. 37–76). Elsevier Academic Press. Teodorescu, K., & Erev, I. (2014). On the Decision to Explore New Alternatives: The Coexistence of Under‐ and Over‐exploration. Journal of Behavioral Decision Making, 27(2), 109–123. Vestewig, R.E. (1977). Extraversion and risk preference in portfolio theory. The Journal of psychology, 97 2d Half, 237-45. Wan, X., Sun, R., Dai, H., Arık, S. Ö., & Pfister, T. (2023). Better zero-shot reasoning with self-adaptive prompting. Findings of the Association for Computational Linguistics: ACL 2023. Wan, Y., Menon, S., & Ramaprasad, A. (2003). How It Happens: A Conceptual Explanation of Choice Overload in Online Decision-Making by Individuals. Americas Conference on Information Systems. Wang, Y., Tree, J. E. F., Walker, M., & Neff, M. (2016). Assessing the impact of hand motion on virtual character personality. ACM Transactions on Applied Perception (TAP), 13(2), 1-23. Weigold, M.F., & Schlenker, B.R. (1991). Accountability and Risk Taking. Personality and Social Psychology Bulletin, 17, 25 - 29. Wester, J., De Jong, S., Pohl, H., & Van Berkel, N. (2024). Exploring people’s perceptions of LLM-generated advice. Computers in Human Behavior: Artificial Humans, 2(2), 100072. Wong, A.S., & Carducci, B.J. (2013). Does Personality Affect Personal Financial Risk Tolerance Behavior. The IUP Journal of Applied Finance, 19, 5-18. Yan, D., & Chen, L. (2023). The influence of personality traits on user interaction with recommendation interfaces. ACM Transactions on Interactive Intelligent Systems, 13(1), 39. Yang, J. C., Dailisan, D., Korecki, M., Hausladen, C. I., & Helbing, D. (2024). LLM Voting: Human Choices and AI Collective Decision Making. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7, 1696–1708. Zeelenberg, Marcel (1999), “Anticipated Regret, Expected Feedback, and Behavioral Decision Making,” Journal of Behavioral Decision Making, 12 (2), 93–106. Zongrone, B.M., Derrick, D.C., & Ligon, G.S. (2015). Individual Differences that Predict Interactions in Mixed-Initiative Teams. Hawaii International Conference on System Sciences, 610-618. Zoria, О., Zoria, S., & Kapaieva, L. (2022). Theoretical and methodological principles of investment risks insurance in their management system. 69. zh_TW
