Scaling Personality Control in LLMs with Big Five Scaler Prompts
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912527369109504 |
|---|---|
| author | Cho, Gunhee Cheong, Yun-Gyung |
| author_facet | Cho, Gunhee Cheong, Yun-Gyung |
| contents | We present Big5-Scaler, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits. By embedding numeric trait values into natural language prompts, our method enables fine-grained personality control without additional training. We evaluate Big5-Scaler across trait expression, dialogue generation, and human trait imitation tasks. Results show that it induces consistent and distinguishable personality traits across models, with performance varying by prompt type and scale. Our analysis highlights the effectiveness of concise prompts and lower trait intensities, providing a efficient approach for building personality-aware dialogue agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling Personality Control in LLMs with Big Five Scaler Prompts Cho, Gunhee Cheong, Yun-Gyung Computation and Language Multiagent Systems We present Big5-Scaler, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits. By embedding numeric trait values into natural language prompts, our method enables fine-grained personality control without additional training. We evaluate Big5-Scaler across trait expression, dialogue generation, and human trait imitation tasks. Results show that it induces consistent and distinguishable personality traits across models, with performance varying by prompt type and scale. Our analysis highlights the effectiveness of concise prompts and lower trait intensities, providing a efficient approach for building personality-aware dialogue agents. |
| title | Scaling Personality Control in LLMs with Big Five Scaler Prompts |
| topic | Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2508.06149 |