Elamur Research⌕
☰
home / papers / 2024 / PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models

PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models

Paper · 2024 · Fiona Anting Tan, Gerard Christopher Yeo, Kokil Jaidka et al.

Summary

The paper asks whether role-play prompts that give an LLM a personality change how well it handles Theory-of-Mind (ToM) reasoning, meaning inferring other agents' beliefs and knowledge. The authors built eight persona prompts from personality psychology and validated psychometric measures: the five Big Five OCEAN traits plus the three Dark Triad traits. The prompts were evaluated on three ToM tasks, namely Belief Understanding (BU), Answerability (AA) and Information Access (IA). The main models were GPT-3.5, Llama 2 and Mistral, with Falcon and Zephyr also appearing in some comparisons. Persona prompting changed ToM performance in measurable and fairly systematic ways. Dark Triad personas shifted results more than Big Five ones, and prosocial traits tended to help. A generic "perspective-taking" role-play prompt did not reliably improve results. The findings are interpreted through psychological theory linking personality to social cognition. The practical lesson is that assigning personas, a common prompt-engineering habit, can quietly weaken an LLM's social-cognitive reasoning, so it calls for caution and auditing.

Key points

  • The eight personas are Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism (OCEAN), plus Machiavellianism, Narcissism and Psychopathy (Dark Triad). A psychology-trained co-author reviewed the prompt wording.
  • IA and AA were scored with weighted F1 and BU with accuracy. Psychopathy and Machiavellianism personas lowered scores on all three tasks, while Agreeableness tended to give the best AA results. Narcissism did not match the positive ToM link reported in the human literature.
  • Models whose ToM scores varied more across personas also proved more controllable on personality tests. Falcon was comparatively resistant to persona prompts.
  • As a robustness check, the authors swapped in the OCEAN descriptions from Jiang et al. (2022) on Mistral 7B. Scores changed by at most about 1.6 points, suggesting the results do not depend on the exact prompt wording.
  • A task-specific perspective-taking prompt raised AA for every model except GPT-3.5. On IA and BU it helped Llama and GPT-3.5 but hurt Falcon, Zephyr and Mistral.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Stanford UniversityStanford · United States434 works · 314,419 citations🎓Tsinghua UniversityBeijing · China333 works · 87,019 citations🎓National University of SingaporeSingapore · Singapore180 works · 34,304 citations🏢AmazonSeattle · United States112 works · 40,565 citations

Also on the byline: NUS Centre for Trusted Internet and Community.

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPsychology · 1,552 worksDevelopmental and Educational Psychology · 499 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksReasoning · 1,426 works

Cite

Cite as Fiona Anting Tan, Gerard Christopher Yeo, Kokil Jaidka, Fanyou Wu, Weijie Xu, Vinija Jain, Aman Chadha, Yang Liu and See-Kiong Ng. 2024. PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models. arXiv:2403.02246.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2403.02246 · arXiv 2403.02246

@misc{tan2024phantom,
  title = {{PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models}},
  author = {Fiona Anting Tan, Gerard Christopher Yeo, Kokil Jaidka, Fanyou Wu, Weijie Xu, Vinija Jain, Aman Chadha, Yang Liu and See-Kiong Ng},
  year = {2024},
  doi = {10.48550/arxiv.2403.02246},
  eprint = {2403.02246},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2403.02246}
}

References

53 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Allport, G. W. 1937. Personality: A psychological interpretation. find
  2. Almazrouei, E.; Alobeidli, H.; Alshamsi, A.; Cappelli, A.; Cojocaru, R.; Debbah, M.; Goffinet, E.; Heslow, D.; Launay, J.; Malartic, Q.; Noune, B.; Pannier, B.; and Penedo, G. 2023. Falcon-40B: an open large language model with state-of-the-art performance. find
  3. Bai, Y.; Ying, J.; Cao, Y.; Lv, X.; He, Y.; Wang, X.; Yu, J.; Zeng, K.; Xiao, Y.; Lyu, H.; et al. 2023. Benchmarking Foundation Models with Language-Model-as-an-Examiner. arXiv preprint arXiv:2306.04181. find
  4. Bang, Y.; Cahyawijaya, S.; Lee, N.; Dai, W.; Su, D.; Wilie, B.; Lovenia, H.; Ji, Z.; Yu, T.; Chung, W.; et al. 2023. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023.
  5. Baron-Cohen, S.; Leslie, A. M.; and Frith, U. 1985. Does the autistic child have a “theory of mind”? Cognition, 21(1): 37–46. find
  6. Baron-Cohen, S.; and Wheelwright, S. 2004. The empathy quotient: an investigation of adults with Asperger syndrome or high functioning autism, and normal sex differences. Journal of autism and developmental disorders, 34: 163–175. Beaudoin, C.; Leblanc, É.; Gagner, C.; and Beauchamp, M. H. 2020. Sy… find
  7. Boyd, R. L.; and Pennebaker, J. W. 2017. Language-based personality: A new approach to personality in a digital world. Current opinion in behavioral sciences, 18: 63–68. find
  8. Bsharat, S. M.; Myrzakhan, A.; and Shen, Z. 2023. Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4. arXiv:2312.16171. — [arXiv:2312.16171](https://arxiv.org/abs/2312.16171) find
  9. Caprara, G. V.; Alessandri, G.; and Eisenberg, N. 2012. Prosociality: the contribution of traits, values, and self-efficacy beliefs. Journal of personality and social psychology, 102(6): 1289. find
  10. Doyle, L. 2020. Anti-Social Cognition: Exploring the Relationships Between the Dark Triad, Empathy, and Theory of Mind. Ph.D. thesis, Trent University (Canada). find
  11. Dutt, R.; Joshi, R.; and Rose, C. 2020. Keeping Up Appearances: Computational Modeling of Face Acts in Persuasion Oriented Discussions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  12. Farha, I. A.; Oprea, S.; Wilson, S.; and Magdy, W. 2022. SemEval-2022 task 6: iSarcasmEval, intended sarcasm detection in English and Arabic. In The 16th International Workshop on Semantic Evaluation 2022, 802–814. Association for Computational Linguistics.
  13. Ferguson, E.; Zhao, K.; O’Carroll, R. E.; and Smillie, L. D. 2019. Costless and costly prosociality: Correspondence among personality traits, economic preferences, and real-world prosociality. Social Psychological and Personality Science, 10(4): 461–471. find
  14. Fink, E.; Begeer, S.; Peterson, C. C.; Slaughter, V.; and de Rosnay, M. 2015. Friends, friendlessness, and the social consequences of gaining a theory of mind. The British Journal of Developmental Psychology, 33(1): 27–30. find
  15. Gallese, V.; and Sinigaglia, C. 2011. What is so special about embodied simulation? Trends in cognitive sciences, 15(11): 512–519. find
  16. Giorgi, S.; Sedoc, J.; Barriere, V.; and Tafreshi, S. 2024. Findings of wassa 2024 shared task on empathy and personality detection in interactions. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, 369–379. find
  17. Goldberg, L. R.; et al. 1999. A broad-bandwidth, public domain, personality inventory measuring the lower-level facets of several five-factor models. Personality psychology in Europe, 7(1): 7–28. find
  18. Gosling, S. D.; Rentfrow, P. J.; and Swann Jr, W. B. 2003. A very brief measure of the Big-Five personality domains. Journal of Research in personality, 37(6): 504–528. find
  19. Gupta, S.; Shrivastava, V.; Deshpande, A.; Kalyan, A.; Clark, P.; Sabharwal, A.; and Khot, T. 2023. Bias runs deep: Implicit reasoning biases in persona-assigned llms. arXiv preprint arXiv:2311.04892. find
  20. Gupta, S.; Shrivastava, V.; Deshpande, A.; Kalyan, A.; Clark, P.; Sabharwal, A.; and Khot, T. 2024. Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs. arXiv:2311.04892. find
  21. Imuta, K.; Henry, J. D.; Slaughter, V.; Selcuk, B.; and Ruff-man, T. 2016. Theory of mind and prosocial behavior in childhood: A meta-analytic review. Developmental psychology, 52(8): 1192. find
  22. Jiang, A. Q.; Sablayrolles, A.; Mensch, A.; Bamford, C.; Chaplot, D. S.; de Las Casas, D.; Bressand, F.; Lengyel, G.; Lample, G.; Saulnier, L.; Lavaud, L. R.; Lachaux, M.; Stock, P.; Scao, T. L.; Lavril, T.; Wang, T.; Lacroix, T.; and Sayed, W. E. 2023. Mistral 7B. CoRR, abs/2310.06825. find
  23. Jiang, G.; Xu, M.; Zhu, S.; Han, W.; Zhang, C.; and Zhu, Y. 2022. MPI: Evaluating and Inducing Personality in Pre-trained Language Models. CoRR, abs/2206.07550. find
  24. John, O. P.; Naumann, L. P.; and Soto, C. J. 2008. Paradigm shift to the integrative big five trait taxonomy. Handbook of personality: Theory and research, 3(2): 114–158. find
  25. John, O. P.; Srivastava, S.; et al. 1999. The Big-Five trait taxonomy: History, measurement, and theoretical perspectives. find
  26. Jonason, P. K.; and Webster, G. D. 2010. The dirty dozen: a concise measure of the dark triad. Psychological assessment, 22(2): 420. find
  27. Jones, D. N.; and Paulhus, D. L. 2014. Introducing the short dark triad (SD3) a brief measure of dark personality traits. Assessment, 21(1): 28–41. find
  28. Kim, H.; Sclar, M.; Zhou, X.; Bras, R.; Kim, G.; Choi, Y.; and Sap, M. 2023. FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions. In Bouamor, H.; Pino, J.; and Bali, K., eds., Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 14397–1441… find
  29. Kojima, T.; Gu, S. S.; Reid, M.; Matsuo, Y.; and Iwasawa, Y. 2022. Large Language Models are Zero-Shot Reasoners. In Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; and Oh, A., eds., Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing…
  30. Kong, A.; Zhao, S.; Chen, H.; Li, Q.; Qin, Y.; Sun, R.; and Zhou, X. 2023. Better Zero-Shot Reasoning with Role-Play Prompting. CoRR, abs/2308.07702. find
  31. Kosinski, M. 2023. Theory of mind may have spontaneously emerged in large language models. arXiv preprint arXiv:2302.02083.
  32. Liu, X.; and Jaidka, K. 2023. I am PsyAM: Modeling Happiness with Cognitive Appraisal Dimensions. In Findings of the Association for Computational Linguistics: ACL 2023, 1192–1210. find
  33. Lu, Y.; Yu, J.; and Huang, S. S. 2023. Illuminating the Black Box: A Psychometric Investigation into the Multifaceted Nature of Large Language Models. CoRR, abs/2312.14202. — [arXiv:2312.14202](https://arxiv.org/abs/2312.14202) find
  34. Lyu, C.; Xu, J.; and Wang, L. 2023. New trends in machine translation using large language models: Case examples with chatgpt. arXiv preprint arXiv:2305.01181. — [arXiv:2305.01181](https://arxiv.org/abs/2305.01181) find
  35. Ma, X.; Gao, L.; and Xu, Q. 2023. ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mind. arXiv preprint arXiv:2305.15068.
  36. McCrae, R. R.; and Costa, P. T. 1987. Validation of the five-factor model of personality across instruments and observers. Journal of personality and social psychology, 52(1): 81. find
  37. McCrae, R. R.; and John, O. P. 1992. An introduction to the five-factor model and its applications. Journal of personality, 60(2): 175–215. find
  38. Nettle, D.; and Liddle, B. 2008. Agreeableness is related to social-cognitive, but not social-perceptual, theory of mind. European Journal of Personality: Published for the European Association of Personality Psychology, 22(4): 323– 335. find
  39. Pérez-Almendros, C.; Anke, L. E.; and Schockaert, S. 2022. SemEval-2022 task 4: Patronizing and condescending language detection. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), 298– 307. find
  40. Premack, D.; and Woodruff, G. 1978. Does the chimpanzee have a theory of mind? Behavioral and brain sciences, 1(4): 515–526. find
  41. Rathje, S.; Mirea, D.-M.; Sucholutsky, I.; Marjieh, R.; Robertson, C. E.; and Van Bavel, J. J. 2024. GPT is an effective tool for multilingual psychological text analysis. Proceedings of the National Academy of Sciences, 121(34): e2308950121. Safdari, M.; Serapio-Garcı́a, G.; Crepy, C.; Fitz, S.; Ro…
  42. Sclar, M.; Choi, Y.; Tsvetkov, Y.; and Suhr, A. 2023. Quantifying Language Models’ Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting. arXiv preprint arXiv:2310.11324. find
  43. Shapira, N.; Zwirn, G.; and Goldberg, Y. 2023. How Well Do Large Language Models Perform on Faux Pas Tests? In Findings of the Association for Computational Linguistics: ACL 2023, 10438–10451. Toronto, Canada: Association for Computational Linguistics. find
  44. Stellwagen, K. K.; and Kerig, P. K. 2013. Dark triad personality traits and theory of mind among school-age children. Personality and Individual Differences, 54(1): 123–127. find
  45. Touvron, H.; Martin, L.; Stone, K.; Albert, P.; Almahairi, A.; Babaei, Y.; Bashlykov, N.; Batra, S.; Bhargava, P.; Bhosale, S.; Bikel, D.; Blecher, L.; Canton-Ferrer, C.; Chen, M.; Cucurull, G.; Esiobu, D.; Fernandes, J.; Fu, J.; Fu, W.; Fuller, B.; Gao, C.; Goswami, V.; Goyal, N.; Hartshorn, A.; Ho… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  46. Tunstall, L.; Beeching, E.; Lambert, N.; Rajani, N.; Rasul, K.; Belkada, Y.; Huang, S.; von Werra, L.; Fourrier, C.; Habib, N.; Sarrazin, N.; Sanseviero, O.; Rush, A. M.; and Wolf, T. 2023. Zephyr: Direct Distillation of LM Alignment. CoRR, abs/2310.16944. find
  47. Udochi, A. L.; Blain, S. D.; Sassenberg, T. A.; Burton, P. C.; Medrano, L.; and DeYoung, C. G. 2022. Activation of the default network during a theory of mind task predicts individual differences in agreeableness and social cognitive ability. Cognitive, Affective, & Behavioral Neuroscience, 1–20. find
  48. Wagner, M. 2020. Agreeableness predicts Theory of Mind in older and younger adults. find
  49. Wellman, H. M. 2018. Theory of mind: The state of the art. European Journal of Developmental Psychology, 15(6): 728–755. find
  50. Wellman, H. M.; Cross, D.; and Watson, J. 2001. Meta-analysis of theory-of-mind development: The truth about false belief. Child development, 72(3): 655–684. find
  51. Wellman, H. M.; Fang, F.; and Peterson, C. C. 2011. Sequential progressions in a theory-of-mind scale: Longitudinal perspectives. Child development, 82(3): 780–792. find
  52. Wimmer, H.; and Perner, J. 1983. Beliefs about beliefs: Representation and constraining function of wrong beliefs in young children’s understanding of deception. Cognition, 13(1): 103–128. find
  53. Wu, X.; Yao, W.; Chen, J.; Pan, X.; Wang, X.; Liu, N.; and Yu, D. 2023. From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning. arXiv:2310.00492. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tan-2024-phantom-persona-based-prompting-has/