Illuminating the Black Box: A Psychometric Investigation into the Multifaceted Nature of Large Language Models

Built on

The Myers-Briggs Type Indicator: Manual (1962)
Myers, I.; and Briggs, K. 1962 · 1962
Earlier work this paper cites.
The Interpretation of Dreams
Sigmund, F. 1997 · 1997
Earlier work this paper cites.
Introducing the Short Dark Triad (SD3): A Brief Measure of Dark Personality Traits
Jones, D. N.; and Paulhus, D. L. 2014 · 2014
Earlier work this paper cites.
Measuring ego development
Loevinger, J.; et al. 2014 · 2014
Earlier work this paper cites.
Open-Source Psychometric Project(OSPP)
OSPP. 2019 · 2019
Earlier work this paper cites.

ChatGPT Can Accurately Predict Public Figures’ Perceived Personalities Without Any Training
Cao, X.; and Kosinski, M. 2023 · 2023
Cited alongside, same era.
Prompt Engineering Guide
Dair.AI. 2023 · 2023
Cited alongside, same era.
Do personality tests generalize to Large Language Models?
Original
Dorner, F. E.; Sühr, T.; Samadi, S.; and Kelava, A. 2023 · 2023
Cited alongside, same era.
AI-powered Bing Chat spills its secrets via prompt injection attack
Edwards, B. 2023 · 2023
Cited alongside, same era.
Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation
Original
Ganesan, A. V.; Lal, Y. K.; Nilsson, A. H.; and Schwartz, H. A. 2023 · 2023
Cited alongside, same era.
Evaluating and Inducing Personality in Pre-trained Language Models
Jiang, G.; Xu, M.; Zhu, S.-C.; Han, W.; Zhang, C.; and Zhu, Y. 2023a
Cited in the paper.
PersonaLLM: Investigating the Ability of Large Language Models to Express Big Five Personality Traits
Original
Jiang, H.; Zhang, X.; Cao, X.; and Kabbara, J. 2023b
Cited in the paper.
Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
Original
Wang, H.; Wang, R.; Mi, F.; Deng, Y.; Wang, Z.; Liang, B.; Xu, R.; and Wong, K.-F. 2023a
Cited in the paper.
Does Role-Playing Chatbots Capture the Character Personalities? Assessing Personality Traits for Role-Playing Chatbots
Original
Wang, X.; Tu, Q.; Fei, Y.; Leng, Z.; and Li, C. 2023b
Cited in the paper.