Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality (2402.14679v2)

Published 22 Feb 2024 in cs.CL and cs.CY

Abstract: In this study, we delve into the validity of conventional personality questionnaires in capturing the human-like personality traits of LLMs. Our objective is to assess the congruence between the personality traits LLMs claim to possess and their demonstrated tendencies in real-world scenarios. By conducting an extensive examination of LLM outputs against observed human response patterns, we aim to understand the disjunction between self-knowledge and action in LLMs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Gordon Willard Allport. 1937. Personality: A psychological interpretation.
  2. Exploring the psychology of gpt-4’s moral and legal reasoning.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  4. Scaling instruction-finetuned language models.
  5. Inducing anxiety in large language models increases exploration and bias.
  6. Paul T Costa and Robert R McCrae. 2008. The revised neo personality inventory (neo-pi-r). The SAGE handbook of personality theory and assessment, 2(2):179–198.
  7. Machine mindset: An mbti exploration of large language models.
  8. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  9. Can ai language models replace human participants? Trends in Cognitive Sciences.
  10. HJ Eysenck. 1988. Eysenck personality questionnaire. Dictionary of behavioral assessment techniques, page 207.
  11. Iason Gabriel. 2020. Artificial intelligence, values, and alignment. Minds and machines, 30(3):411–437.
  12. Lewis R Goldberg. 1981. Language and individual differences: The search for universals in personality lexicons. Review of personality and social psychology, 2(1):141–165.
  13. Xue-Ying GU and Shi Hu. 2012. Mbti: New development and application. Advances in Psychological Science, 20(10):1700.
  14. Ai language models cannot replace human research participants. Ai & Society, pages 1–3.
  15. Edward Helmes and John R Reddon. 1993. A perspective on developments in assessing psychopathology: A critical review of the mmpi and mmpi-2. Psychological Bulletin, 113(3):453.
  16. Who is chatgpt? benchmarking llms’ psychological portrayal using psychobench.
  17. Evaluating and inducing personality in pre-trained language models.
  18. Personallm: Investigating the ability of large language models to express big five personality traits.
  19. The lexical approach to personality: A historical review of trait taxonomic research. European journal of Personality, 2(3):171–203.
  20. Estimating the personality of white-box language models.
  21. A reliability meta-analysis for 44 items big five inventory: Based on the reliability generalization methodology. Advances in Psychological Science, 23(5):755.
  22. Does gpt-3 demonstrate psychopathy? evaluating large language models from a psychological perspective.
  23. Kirti Makwana and Dr Govind B Dave. 2020. Confirmatory factor analysis of neris type explorer® scale–a tool for personality assessment. International Journal of Management, 11(9).
  24. Who is GPT-3? an exploration of personality, values and demographics. In Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), pages 218–227, Abu Dhabi, UAE. Association for Computational Linguistics.
  25. Isabel Briggs Myers. 1962. The myers-briggs type indicator: Manual (1962).
  26. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744.
  27. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
  28. The power of personality: The comparative validity of personality traits, socioeconomic status, and cognitive ability for predicting important life outcomes. Perspectives on Psychological science, 2(4):313–345.
  29. Brent W Roberts and Hee J Yoon. 2022. Personality psychology. Annual review of psychology, 73:489–516.
  30. Do gpt language models suffer from split personality disorder? the advent of substrate-free psychometrics.
  31. The self-perception and political biases of chatgpt.
  32. Gerard Saucier and Lewis R Goldberg. 2001. Lexical studies of indigenous personality factors: Premises, products, and prospects. Journal of personality, 69(6):847–879.
  33. Evaluating the moral beliefs encoded in llms.
  34. Attention is all you need. Advances in neural information processing systems, 30.
  35. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems, 32.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Yiming Ai (5 papers)
  2. Zhiwei He (42 papers)
  3. Ziyin Zhang (16 papers)
  4. Wenhong Zhu (8 papers)
  5. Hongkun Hao (11 papers)
  6. Kai Yu (201 papers)
  7. Lingjun Chen (3 papers)
  8. Rui Wang (996 papers)
Citations (6)
X Twitter Logo Streamline Icon: https://streamlinehq.com