Can Large Language Models Personalize Dialogues to Generational Styles?

Pier Felice Balestrucci, Ondrej Dusek, Luca Anselma, Alessandro Mazzei


Abstract
We investigate how large language models (LLMs) can produce personalized dialogue responses, specifically focusing on whether they reflect linguistic styles pertaining to different generations: Baby Boomers, Generation X, Generation Y, and Generation Z. We create P-MultiWoZ, a personalized, generation-specific version of MultiWOZ 2.2, by prompting LLMs, and validate its alignment with the original dataset through automatic and human evaluations. To validate the appropriateness of generational linguistic traits, we introduce GeMoSC, a corpus of generation-annotated movie dialogues. Linguistic analysis and perplexity test suggest that P-MultiWoZ reflects patterns consistent with GeMoSC. Finally, a human evaluation reveals that annotators were able to mostly correctly identify the generation behind P-MultiWoZ dialogues, based only on a single query-reply pair.
Anthology ID:
2025.findings-emnlp.5
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–77
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.5/
DOI:
Bibkey:
Cite (ACL):
Pier Felice Balestrucci, Ondrej Dusek, Luca Anselma, and Alessandro Mazzei. 2025. Can Large Language Models Personalize Dialogues to Generational Styles?. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 64–77, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Can Large Language Models Personalize Dialogues to Generational Styles? (Balestrucci et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.5.pdf
Checklist:
 2025.findings-emnlp.5.checklist.pdf