The Self-Perception and Political Biases of ChatGPT

This contribution analyzes the self-perception and political biases of OpenAI's Large Language Model ChatGPT. Taking into account the first small-scale reports and studies that have emerged, claiming that ChatGPT is politically biased towards progressive and libertarian points of view, this contribution aims to provide further clarity on this subject. For this purpose, ChatGPT was asked to answer the questions posed by the political compass test as well as similar questionnaires that are specific to the respective politics of the G7 member states. These eight tests were repeated ten times each and revealed that ChatGPT seems to hold a bias towards progressive views. The political compass test revealed a bias towards progressive and libertarian views, with the average coordinates on the political compass being (-6.48, -5.99) (with (0, 0) the center of the compass, i.e., centrism and the axes ranging from -10 to 10), supporting the claims of prior research. The political questionnaires for the G7 member states indicated a bias towards progressive views but no significant bias between authoritarian and libertarian views, contradicting the findings of prior reports, with the average coordinates being (-3.27, 0.58). In addition, ChatGPT's Big Five personality traits were tested using the OCEAN test and its personality type was queried using the Myers-Briggs Type Indicator (MBTI) test. Finally, the maliciousness of ChatGPT was evaluated using the Dark Factor test. These three tests were also repeated ten times each, revealing that ChatGPT perceives itself as highly open and agreeable, has the Myers-Briggs personality type ENFJ, and is among the 15% of test-takers with the least pronounced dark traits.

[1]  David Rozado.  The Political Biases of ChatGPT , 2023, Social Sciences.

[2]  Nanyang Technological University,et al.  A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT , 2023, ArXiv.

[3]  Jochen Hartmann,et al.  The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation , 2023, SSRN Electronic Journal.

[4]  Valdemar Pinho Neto,et al.  More human than human: measuring ChatGPT political bias , 2023, SSRN Electronic Journal.

[5]  Robert W. McGee.  Who Were the 10 Best and 10 Worst U.S. Presidents?The Opinion of Chat GPT (Artificial Intelligence) , 2023, SSRN Electronic Journal.

[6]  Robert W. McGee.  Is Chat Gpt Biased Against Conservatives? An Empirical Study , 2023, SSRN Electronic Journal.

[7]  Christopher D. Manning.  Human Language Understanding & Reasoning , 2022, Daedalus.

[8]  B. Hilbig,et al.  Stability and Change: The Dark Factor of Personality Shapes Dark Traits , 2020, Social Psychological and Personality Science.

[9]  Hassan B. Kazemian,et al.  Machine Learning Approach to Personality Type Prediction Based on the Myers-Briggs Type Indicator® , 2020, Multimodal Technol. Interact..

[10]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[11]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[12]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[13]  B. Hilbig,et al.  The Dark Core of Personality , 2018, Psychological review.

[14]  Maite D. Laméris,et al.  An Experimental Test of the Validity of Survey-Measured Political Ideology , 2018, SSRN Electronic Journal.

[15]  Alec Radford,et al.  Improving Language Understanding by Generative Pre-Training , 2018 .

[16]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[17]  Colin G. DeYoung,et al.  Gender Differences in Personality across the Ten Aspects of the Big Five , 2011, Front. Psychology.

[18]  Gregory A. Huber,et al.  The Big Five Personality Traits in the Political Arena , 2011 .

[19]  David J. Pittenger,et al.  The Utility of the Myers-Briggs Type Indicator , 1993 .

[20]  I. B. Myers.  The Myers-Briggs Type Indicator: Manual (1962). , 1962 .

[21]  I. B. Myers.  The myers-briggs type indicator , 1962 .

[22]  D. W. Fiske.  Consistency of the factorial structures of personality ratings from different sour sources. , 1949, Journal of abnormal psychology.