Enhancing AI Dialogue through Dual Role Assignment: An Investigation of User-AI Professional Role Sharing
DOI:
https://doi.org/10.51094/jxiv.1014Keywords:
Large Language Models (LLM), Prompt Engineering, Role Theory, Framing Theory, User-AI Role AssignmentAbstract
While conversational AI systems like ChatGPT, Claude, and Gemini are increasingly utilized across various domains, previous research has primarily focused on assigning professional roles (e.g., physician, historian) to AI models alone. This study empirically investigates how dialogue content transforms when professional roles are assigned to both users and AI. Through analysis of dialogues about identical visual stimuli under four conditions (no-role/AI-only role/user-only role/both roles), we demonstrate that role assignment significantly influences response characteristics. Quantitative analysis reveals increased use of specialized terminology, while qualitative analysis shows enhanced expertise and multiperspectivity, particularly in the both-role condition. These findings suggest that user-side role assignment can be an effective prompt engineering strategy for deepening AI-human dialogue, with implications for educational tools and expert support systems.
Conflicts of Interest Disclosure
There are no conflicts of interest (COI) to disclose regarding this research.Downloads *Displays the aggregated results up to the previous day.
References
Bozkurt, A., Sharma, R.C.: Generative AI and Prompt Engineering: The Art of Whispering to Let the Genie Out of the Algorithmic World. International Journal of Educational Technology in Higher Education, 20(1), pp. 1-15 (2023)
Bansal, P.: Prompt Engineering Importance and Applicability with Generative AI. Journal of Computational Creativity, 12(10), pp. 217-329 (2024)
Bertalan, M.: The Evolution of Conversational AI: From Chatbots to Large Language Models. Journal of Artificial Intelligence Research, 78, pp. 45-72 (2023)
Giray, L.: Prompt Engineering with ChatGPT: A Guide for Academic Writers. Journal of Academic Writing and Publishing, 39(4), pp. 2625--2635 (2023)
Chen, B., Zhang, Z., Langrené, N., Zhu, S.: Unleashing the Potential of Prompt Engineering in Large Language Models: A Comprehensive Review. ACM Transactions on Intelligent Systems and Technology, 15(2), pp. 1-25 (2024)
Lin, J., Tomlin, N., Andreas, J., Eisner, J.: Decision-oriented Dialogue for Human-AI Collaboration. Transactions of the Association for Computational Linguistics, 12(1), pp. 100-123 (2024)
Cain, W.: Prompting Change: Exploring Prompt Engineering in Large Language Model AI and Its Potential to Transform Education. International Journal of Instructional Technology and Distance Learning, 8(3), pp. 45-59 (2024)
Biddle, B.J.: Recent Developments in Role Theory. Annual Review of Sociology, 12(1), pp. 67-92 (1986)
Entman, R.M.: Framing: Toward Clarification of a Fractured Paradigm. Journal of Communication, 43(4), pp. 51-58 (1993)
Nistor, N., Chiru, C.-G., Bresser, N.: Online Knowledge Communities as Dialogic Learning Spaces: Voice, Structure, and Bridging. International Journal of Computer-Supported Collaborative Learning, 9(2), pp. 141-158 (2014)
Fernandes, U.d.S., Logeswaran, L., Bresser, N.: Lessons Learned from Modeling the Interaction with Conversational Agents. IxD&A, 52, pp. 23-35 (2022)
Scholten, M.R., Kelders, S.M., Van Gemert-Pijnen, J.E.W.C.: Similarity in Action with an Embodied Conversational Agent: Can Synchronous Speech Yield Higher Levels of Rapport? IxD&A, 56(7), pp. 131-155 (2023)
Aslan, I., Neu, D., Neupert, D., Grafberger, S., Weise, N., Pfeil, P., Kuschewski, M.: How to Compliment a Human - Designing Affective and Well-being Promoting Conversational Things. IxD&A, 58(7), pp. 157-180 (2023)
PROSPECT Repository (2024). https://doi.org/10.5281/zenodo.14567800
Downloads
Posted
Submitted: 2024-12-29 02:09:36 UTC
Published: 2025-01-15 06:02:52 UTC
License
Copyright (c) 2025
Keisuke Sato
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
