Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.19852 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912727583162368 |
|---|---|
| author | Dai, Shi-Wei Shie, Yan-Wei Yang, Tsung-Huan Ku, Lun-Wei Li, Yung-Hui |
| author_facet | Dai, Shi-Wei Shie, Yan-Wei Yang, Tsung-Huan Ku, Lun-Wei Li, Yung-Hui |
| contents | Personalized Large Language Models (LLMs) have been shown to be an effective way to create more engaging and enjoyable user-AI interactions. While previous studies have explored using prompts to elicit specific personality traits in LLMs, they have not optimized these prompts to maximize personality expression. To address this limitation, we propose PersonaPulse: Dynamic Profile Optimization for Realistic Personality Expression in LLMs, a framework that leverages LLMs' inherent knowledge of personality traits to iteratively enhance role-play prompts while integrating a situational response benchmark as a scoring tool, ensuring a more realistic and contextually grounded evaluation to guide the optimization process. Quantitative evaluations demonstrate that the prompts generated by PersonaPulse outperform those of prior work, which were designed based on personality descriptions from psychological studies. Additionally, we explore the relationship between model size and personality modeling through extensive experiments. Finally, we find that, for certain personality traits, the extent of personality evocation can be partially controlled by pausing the optimization process. These findings underscore the importance of prompt optimization in shaping personality expression within LLMs, offering valuable insights for future research on adaptive AI interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19852 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Profile-LLM: Dynamic Profile Optimization for Realistic Personality Expression in LLMs Dai, Shi-Wei Shie, Yan-Wei Yang, Tsung-Huan Ku, Lun-Wei Li, Yung-Hui Computation and Language Personalized Large Language Models (LLMs) have been shown to be an effective way to create more engaging and enjoyable user-AI interactions. While previous studies have explored using prompts to elicit specific personality traits in LLMs, they have not optimized these prompts to maximize personality expression. To address this limitation, we propose PersonaPulse: Dynamic Profile Optimization for Realistic Personality Expression in LLMs, a framework that leverages LLMs' inherent knowledge of personality traits to iteratively enhance role-play prompts while integrating a situational response benchmark as a scoring tool, ensuring a more realistic and contextually grounded evaluation to guide the optimization process. Quantitative evaluations demonstrate that the prompts generated by PersonaPulse outperform those of prior work, which were designed based on personality descriptions from psychological studies. Additionally, we explore the relationship between model size and personality modeling through extensive experiments. Finally, we find that, for certain personality traits, the extent of personality evocation can be partially controlled by pausing the optimization process. These findings underscore the importance of prompt optimization in shaping personality expression within LLMs, offering valuable insights for future research on adaptive AI interactions. |
| title | Profile-LLM: Dynamic Profile Optimization for Realistic Personality Expression in LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.19852 |