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

Driving Generative Agents With Their Personality (2402.14879v1)

Published 21 Feb 2024 in cs.CL and cs.AI

Abstract: This research explores the potential of LLMs to utilize psychometric values, specifically personality information, within the context of video game character development. Affective Computing (AC) systems quantify a Non-Player character's (NPC) psyche, and an LLM can take advantage of the system's information by using the values for prompt generation. The research shows an LLM can consistently represent a given personality profile, thereby enhancing the human-like characteristics of game characters. Repurposing a human examination, the International Personality Item Pool (IPIP) questionnaire, to evaluate an LLM shows that the model can accurately generate content concerning the personality provided. Results show that the improvement of LLM, such as the latest GPT-4 model, can consistently utilize and interpret a personality to represent behavior.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (10)
  1. GAMYGDALA: An emotion engine for games, IEEE Transactions on Affective Computing 5 (2014) 32–44. doi:10.1109/T-AFFC.2013.24, conference Name: IEEE Transactions on Affective Computing.
  2. A. Shirvani, S. Ware, A formalization of emotional planning for strong-story systems, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 16 (2020) 116–122. URL: https://ojs.aaai.org/index.php/AIIDE/article/view/7419. doi:10.1609/aiide.v16i1.7419, number: 1.
  3. L. J. Klinkert, C. Clark, Artificial psychosocial framework for affective non-player characters, in: H. R. Arabnia, K. Ferens, D. de la Fuente, E. B. Kozerenko, J. A. Olivas Varela, F. G. Tinetti (Eds.), Advances in Artificial Intelligence and Applied Cognitive Computing, Transactions on Computational Science and Computational Intelligence, Springer International Publishing, 2021, pp. 695–714. doi:10.1007/978-3-030-70296-0_50.
  4. Large language models and the perils of their hallucinations, Critical Care 27 (2023) 120. URL: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10032023/. doi:10.1186/s13054-023-04393-x.
  5. URL: https://toyokeizai.net/articles/-/673424.
  6. I. Millington, Artificial neural networks, in: AI for Games, 3rd ed., CRC Press, 2019, p. 1031. URL: https://www.oreilly.com/library/view/ai-for-games/9781351053280/, ISBN: 9781351053280.
  7. L. R. Goldberg, The development of markers for the big-five factor structure, Psychological Assessment 4 (1992) 26–42. doi:10.1037/1040-3590.4.1.26, place: US Publisher: American Psychological Association.
  8. URL: http://www.handresearch.com/diagnostics/system-for-big-five-personality-profile-interpretation-derived-from-personality-disorder-prototypes.htm.
  9. URL: http://openpsychometrics.org/_rawdata/.
  10. URL: https://ipip.ori.org/.
Citations (3)

Summary

We haven't generated a summary for this paper yet.