journal article·2025-07-22Open access

Generative Language Models for Personality-Based Utterances in Novels: A Character Clustering Approach

Eun-Jin Kim, Chung-Hwan Joe, Misun Yun, Young-Seob Jeong

Applied Sciences· Volume 15· Issue 15

Abstract

In novels, readers encounter a variety of characters with distinct personalities, and their satisfaction tends to increase when each character’s utterances consistently reflect their unique traits. Recent advances in large language model (LLM) technology have made it possible to perform complex tasks such as generating long-form narratives and adapting writing styles. However, research on generating character utterances that reflect individual personalities remains limited. In this paper, we identify a key challenge in this task, namely the unconscious influence of the author’s writing style, and propose a novel clustering-based method to mitigate this problem by tuning large language models. We manually annotated Big Five personality trait scores for characters appearing in selected novels and designed prompts to generate examples for instruction-tuning. Experimental results demonstrate that language models trained using our proposed method produce utterances that more consistently reflect character personalities compared to untuned models.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Authorship Attribution and Profiling · Topic Modeling · Advanced Text Analysis Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea

Department of English Language and Literature, Hongik University, Seoul 04066, Republic of Korea

Division of English and European Studies, Inha University, Incheon 22209, Republic of Korea

Funding

Ministry of Education of the Republic of Korea · National Research Foundation of Korea · Hongik University new faculty research

References (51)

Show source-provided references
1. Language models are few-shot learners
2. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., and Azhar, F. (2023). Llama: Open and efficient foundation language models. arXiv.
3. On the effectiveness of large language models in domain-specific code generation10.1145/3715008 ↗
4. Large language models encode clinical knowledge10.1038/s41586-023-06291-2 ↗
5. Toward expert-level medical question answering with large language models10.1038/s41591-024-03423-7 ↗
6. Garrido-Merchán, E.C., Arroyo-Barrigüete, J.L., and Gozalo-Brizuela, R. (2023). Simulating HP Lovecraft horror literature with the ChatGPT large language model. arXiv.
7. Rashkin, H., Celikyilmaz, A., Choi, Y., and Gao, J. (2020). Plotmachines: Outline-conditioned generation with dynamic plot state tracking. arXiv.10.18653/v1/2020.emnlp-main.349 ↗
8. Liu, D., Li, J., Yu, M.H., Huang, Z., Liu, G., Zhao, D., and Yan, R. (2020, January 7–12). A character-centric neural model for automated story generation. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.
9. Zhu, J., and Jurgens, D. (2021). Idiosyncratic but not arbitrary: Learning idiolects in online registers reveals distinctive yet consistent individual styles. arXiv.10.18653/v1/2021.emnlp-main.25 ↗
10. Jafariakinabad, F., and Hua, K.A. (2019, January 16–19). Style-Aware Neural Model with Application in Authorship Attribution. Proceedings of the 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), Boca Raton, FL, USA.10.1109/ICMLA.2019.00061 ↗
11. Leech, G.N., and Short, M. (2007). Style in Fiction: A linguistic Introduction to English Fictional Prose, Pearson Education. Number 13.
12. Stylometric analysis of Early Modern period English plays10.1093/llc/fqx059 ↗
13. Creating fictional characters: The role of experience, personality, and social processes10.1037/aca0000094 ↗
14. Wu, W., Wu, H., Jiang, L., Liu, X., Hong, J., Zhao, H., and Zhang, M. (2024). From role-play to drama-interaction: An LLM solution. arXiv.10.18653/v1/2024.findings-acl.196 ↗
15. Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., and Weston, J. (2018). Personalizing dialogue agents: I have a dog, do you have pets too?. arXiv.10.18653/v1/P18-1205 ↗
16. Linguistic styles: Language use as an individual difference10.1037/0022-3514.77.6.1296 ↗
17. Personality trait structure as a human universal10.1037/0003-066X.52.5.509 ↗
18. Doyle, A.C. (1892). The Adventure of the Blue Carbuncle. The Adventures of Sherlock Holmes, George Newnes. Available online: https://www.gutenberg.org/ebooks/1661.
19. Doyle, A.C. (1892). A Scandal in Bohemia. The Adventures of Sherlock Holmes, George Newnes. Available online: https://www.gutenberg.org/ebooks/1661.
20. Validation of the five-factor model of personality across instruments and observers10.1037/0022-3514.52.1.81 ↗
21. Attention is all you need
22. Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2025, April 29). Improving language understanding by generative pre-training. Available online: https://openai.com/index/language-unsupervised/.
23. Language models are unsupervised multitask learners
24. Team, G., Anil, R., Borgeaud, S., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., and Millican, K. (2023). Gemini: A family of highly capable multimodal models. arXiv.
25. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., and Bhosale, S. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv.
26. Almazrouei, E., Alobeidli, H., Alshamsi, A., Cappelli, A., Cojocaru, R., Debbah, M., Goffinet, É., Hesslow, D., Launay, J., and Malartic, Q. (2023). The falcon series of open language models. arXiv.
27. Team, G., Mesnard, T., Hardin, C., Dadashi, R., Bhupatiraju, S., Pathak, S., Sifre, L., Rivière, M., Kale, M.S., and Love, J. (2024). Gemma: Open models based on gemini research and technology. arXiv.
28. Team, G., Riviere, M., Pathak, S., Sessa, P.G., Hardin, C., Bhupatiraju, S., Hussenot, L., Mesnard, T., Shahriari, B., and Ramé, A. (2024). Gemma 2: Improving open language models at a practical size. arXiv.
29. Biderman, S., Schoelkopf, H., Anthony, Q.G., Bradley, H., O’Brien, K., Hallahan, E., Khan, M.A., Purohit, S., Prashanth, U.S., and Raff, E. (2023, January 23–29). Pythia: A suite for analyzing large language models across training and scaling. Proceedings of the International Conference on Machine Learning. PMLR, Honolulu, HI, USA.
30. Jiang, A.Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D.S., de Las Casas, D., Bressand, F., Lengyel, G., Lample, G., and Saulnier, L. (2023). Mistral 7B. arXiv.
31. Palm: Scaling language modeling with pathways
32. John, O.P., Robins, R.W., and Pervin, L.A. (2010). Handbook of Personality: Theory and Research, Guilford Press. [3rd ed.].
33. Vishnubhotla, K., Hammond, A., and Hirst, G. (2022). The project dialogism novel corpus: A dataset for quotation attribution in literary texts. arXiv.
34. Masumura, R., Orihashi, S., Ihori, M., Tanaka, T., Makishima, N., Suzuki, S., Mizuno, S., and Hojo, N. (March, January 25). Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level Scores. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.
35. Cohen, J. (2013). Statistical Power Analysis for the Behavioral Sciences, Routledge.10.4324/9780203771587 ↗
36. Intraclass correlations: Uses in assessing rater reliability10.1037/0033-2909.86.2.420 ↗
37. Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology10.1037/1040-3590.6.4.284 ↗
38. Nekvinda, T., and Dušek, O. (2022). AARGH! end-to-end retrieval-generation for task-oriented dialog. arXiv.10.18653/v1/2022.sigdial-1.29 ↗
39. Passali, T., Chatzikyriakidis, E., Andreadis, S., Stavropoulos, T.G., Matonaki, A., Fachantidis, A., and Tsoumakas, G. (2023). From lengthy to lucid: A systematic literature review on NLP techniques for taming long sentences. arXiv.
40. Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv.
41. Hu, E., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, L., and Chen, W. (2022). LoRA: Low-Rank Adaptation of Large Language Models. arXiv.
42. Paszke, A. (2019). Pytorch: An imperative style, high-performance deep learning library. arXiv.
43. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., and Funtowicz, M. (2020, January 16–20). Transformers: State-of-the-art natural language processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online.10.18653/v1/2020.emnlp-demos.6 ↗
44. Dubois, Y., Galambosi, B., Liang, P., and Hashimoto, T.B. (2024). Length-controlled alpacaeval: A simple way to debias automatic evaluators. arXiv.
45. Peng, B., Li, C., He, P., Galley, M., and Gao, J. (2023). Instruction tuning with gpt-4. arXiv.
46. Liusie, A., Manakul, P., and Gales, M.J.F. (2024). LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models. arXiv.10.18653/v1/2024.eacl-long.8 ↗
47. Wang, P., Li, L., Chen, L., Cai, Z., Zhu, D., Lin, B., Cao, Y., Liu, Q., Liu, T., and Sui, Z. (2023). Large language models are not fair evaluators. arXiv.
48. Llm evaluators recognize and favor their own generations
49. Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cappelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., and Launay, J. (2023). The Refined-Web dataset for Falcon LLM: Outperforming curated corpora with web data, and web data only. arXiv.
50. Stephenson, N. (1992). Snow Crash, Penguin Books.
51. Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling laws for neural language models. arXiv.