Abstract
This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models’ responses to opinion-related questions on specified topics since an individual’s personality often manifests in the form of their expressed opinions, thereby showcasing different personality traits. Specifically, we construct PersonalityEdit, a new benchmark dataset to address this task. Drawing on the theory in Social Psychology [10], we isolate three representative traits, namely Neuroticism, Extraversion, and Agreeableness, as the foundation for our benchmark. We then gather data using GPT-4, generating responses that align with a specified topic and embody the targeted personality trait. We conduct comprehensive experiments involving various baselines and discuss the representation of personality behavior in LLMs. Our findings uncover potential challenges of the proposed task, illustrating several remaining issues. We anticipate that our work can stimulate further annotation in model editing and personality-related research.
Code is available at https://github.com/zjunlp/EasyEdit.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ackerman, P.L., Heggestad, E.D.: Intelligence, personality, and interests: evidence for overlapping traits. Psychol. Bull. 121(2), 219 (1997)
Akata, E., Schulz, L., Coda-Forno, J., et al.: Playing repeated games with large language models. CoRR abs/2305.16867 (2023)
et al., E.M.: Memory-based model editing at scale. In: ICML 2022, vol. 162, pp. 15817–15831 (2022)
Caron, G., Srivastava, S.: Manipulating the perceived personality traits of language models. In: Findings of EMNLP, Singapore, December 6-10, 2023, pp. 2370–2386
Costa, P.T., Jr., McCrae, R.R.: Domains and facets: hierarchical personality assessment using the revised neo personality inventory. J. Pers. Assess. 64(1), 21–50 (1995)
DeYoung, C.G., Hirsh, J.B., Shane, M.S., Papademetris, X., Rajeevan, N., Gray, J.R.: Testing predictions from personality neuroscience: Brain structure and the big five. Psychol. Sci. 21(6), 820–828 (2010)
Flekova, L., Gurevych, I.: Personality profiling of fictional characters using sense-level links between lexical resources. In: EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pp. 1805–1816 (2015)
Funder, D.C.: Accurate personality judgment. Current Directions in Psychological Sci. 21(3), 177–182 (2012). https://doi.org/10.1177/0963721412445309
Goldberg, L.R.: Language and individual differences: the search for universals in personality lexicons. Rev. Personality Soc. Psychol. 2(1), 141–165 (1981)
Goldberg, L.R.: An alternative description of personality: the big-five factor structure. J. Pers. Soc. Psychol. 59(6), 1216 (1990)
Hartvigsen, T., Sankaranarayanan, S., et al.: Aging with GRACE: lifelong model editing with discrete key-value adaptors. CoRR abs/2211.11031 (2022)
Helbig, D., Troiano, E., Klinger, R.: Challenges in emotion style transfer: An exploration with a lexical substitution pipeline. In: Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media, SocialNLP@ACL 2020, Online, July 10, 2020, pp. 41–50
Hunston, S.: Corpus approaches to evaluation: Phraseology and evaluative language, vol. 13. Routledge (2010)
Jiang, G., Xu, M., Zhu, S., Han, W., Zhang, C., Zhu, Y.: MPI: evaluating and inducing personality in pre-trained language models. CoRR abs/2206.07550 (2022)
Jiang, H., Zhang, X., et al.: Personallm: investigating the ability of GPT-3.5 to express personality traits and gender differences. CoRR abs/2305.02547 (2023)
Jiang, H., Zhang, X., Choi, J.D.: Automatic text-based personality recognition on monologues and multiparty dialogues using attentive networks and contextual embeddings (student abstract). In: AAAI, pp. 13821–13822. AAAI Press (2020)
Jukic, J., Vukojevic, I., Snajder, J.: You are what you talk about: Inducing evaluative topics for personality analysis. In: Findings of EMNLP, 2022, pp. 3986–3999
Keh, S.S., Cheng, I.: Myers-briggs personality classification and personality-specific language generation using pre-trained language models. CoRR abs/1907.06333
Larson, L.M., et al.: Meta-analyses of big six interests and big five personality factors. J. Vocat. Behav. 61(2), 217–239 (2002)
Li, X., Li, Y., et al.: Is GPT-3 a psychopath? evaluating large language models from a psychological perspective. CoRR abs/2212.10529 (2022)
Liu, A., Wang, A., Okazaki, N.: Semi-supervised formality style transfer with consistency training. In: ACL 2022, Dublin, Ireland, May 22-27, 2022, pp. 4689–4701 (2022)
Liu, Y., et al.: Roberta: A robustly optimized BERT pretraining approach. CoRR abs/1907.11692 (2019)
Madaan, A., et al., A.S.: Politeness transfer: A tag and generate approach. In: ACL 2020, Online, July 5-10, pp. 1869–1881 (2020)
Mallen, A., et al.: When not to trust language models: investigating effectiveness and limitations of parametric and non-parametric memories. CoRR abs/2212.10511 (2022)
Meng, K., et al.: Mass-editing memory in a transformer. CoRR abs/2210.07229
Meng, K., Bau, D., Andonian, A., Belinkov, Y.: Locating and editing factual associations in GPT. In: NeurIPS (2022)
Miotto, M., Rossberg, N., Kleinberg, B.: Who is GPT-3? an exploration of personality, values and demographics. In: Workshop on NLP+CSS, pp. 218–227 (2022)
Mitchell, E., et al.: Fast model editing at scale. In: ICLR 2022
Myers, I.B.: The myers-briggs type indicator: Manual (1962) (1962)
OpenAI: Gpt-4 technical report (2023)
Pan, K., Zeng, Y.: Do llms possess a personality? making the MBTI test an amazing evaluation for large language models. CoRR abs/2307.16180
Park, J.S., O’Brien, J.C., et al.: Generative agents: Interactive simulacra of human behavior. CoRR abs/2304.03442 (2023)
Pennebaker, J.W., King, L.A.: Linguistic styles: language use as an individual difference. J. Pers. Soc. Psychol. 77(6), 1296 (1999)
Safdari, M., Serapio-García, G., Crepy, C., et al.: Personality traits in large language models. CoRR abs/2307.00184 (2023)
Schwartz, H.A., et al.: Personality, gender, and age in the language of social media: the open-vocabulary approach. PLoS ONE 8(9), e73791 (2013)
Shanahan, M., et al.: Role-play with large language models. CoRR abs/2305.16367 (2023)
Stewart, R.D., et al.: The finer details? the predictability of life outcomes from big five domains, facets, and nuances. J. Pers. 90(2), 167–182 (2022)
Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models (2023)
Tu, Q., et al.: Characterchat: learning towards conversational AI with personalized social support. CoRR abs/2308.10278 (2023)
Wang, B., Komatsuzaki, A.: Gpt-j-6b: a 6 billion parameter autoregressive language model (2021). https://github.com/kingoflolz/mesh-transformer-jax
Wang, P., Zhang, N., et al.: Easyedit: an easy-to-use knowledge editing framework for large language models. CoRR abs/2308.07269 (2023)
Wen, Z., et al.: Desprompt: personality-descriptive prompt tuning for few-shot personality recognition. Inf. Process. Manage. 60(5), 103422 (2023)
Xi, Z., et al.: The rise and potential of large language model based agents: A survey. CoRR abs/2309.07864 (2023)
Yang, F., et al.: Learning to answer psychological questionnaire for personality detection. In: Findings of EMNLP 2021, pp. 1131–1142 (2021)
Yao, Y., et al.: Editing large language models: Problems, methods, and opportunities. CoRR abs/2305.13172 (2023)
Yao, Y., et al.: Knowledge rumination for pre-trained language models. CoRR abs/2305.08732 (2023)
Yao, Z., Yu, H.: Improving formality style transfer with context-aware rule injection. In: ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp. 1561–1570 (2021)
Yin, X., et al.: History matters: temporal knowledge editing in large language model. CoRR abs/2312.05497 (2023)
Zhao, W.X., et al.: A survey of large language models. CoRR abs/2303.18223 (2023)
Zheng, C., et al.: Can we edit factual knowledge by in-context learning? CoRR abs/2305.12740 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mao, S. et al. (2025). Editing Personality For Large Language Models. In: Wong, D.F., Wei, Z., Yang, M. (eds) Natural Language Processing and Chinese Computing. NLPCC 2024. Lecture Notes in Computer Science(), vol 15360. Springer, Singapore. https://doi.org/10.1007/978-981-97-9434-8_19
Download citation
DOI: https://doi.org/10.1007/978-981-97-9434-8_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-9433-1
Online ISBN: 978-981-97-9434-8
eBook Packages: Computer ScienceComputer Science (R0)