Research
Scaling Personality Control in LLMs with Big Five Scaler Prompts
arXiv:2508.06149v2 Announce Type: replace Abstract: We present Big5-Scaler, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits. By emb
arXiv:2508.06149v2 Announce Type: replace Abstract: 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.
Related
- Neuron-based Personality Trait Induction in Large Language Models
- A closer look at how large language models trust humans: patterns and biases
- How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
Source: arXiv cs.CL | 2026-10-15