Scaling Personality Control in LLMs with Big Five Scaler Prompts

2025-08-08

AI Summary

This study addresses the challenge of zero-shot, fine-grained controllability of the Big Five personality traits (Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism) in large language models (LLMs) without parameter updates. We propose Big5-Scaler, a framework that quantifies each trait along a continuous intensity scale and directly encodes these numerical values into natural language prompts—enabling zero-shot, cross-model-consistent personality control. Our method integrates numerically grounded prompt engineering with conditional generation, eliminating the need for fine-tuning or auxiliary parameters. Evaluation on dialogue generation and personality imitation tasks demonstrates substantial improvements in both accuracy and consistency of target trait expression. Human evaluations confirm high perceptibility and stability across diverse LLMs. Crucially, effective control is achieved using only concise prompts and low-intensity settings, underscoring the pivotal role of prompt design in computational personality modeling.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Large language models for search

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.

Problem

• Control LLM personality traits using prompt-based framework
• Enable fine-grained personality adjustment without model retraining
• Evaluate effectiveness across trait expression and dialogue tasks

Innovation

• Prompt-based framework for personality control
• Embedding numeric traits in prompts
• No additional training required