SAC: A Framework for Measuring and Inducing Personality Traits in LLMs with Dynamic Intensity Control

TL;DR

This work addresses the need for fine-grained, continuous personality control in LLMs by replacing coarse Big Five assessments with Cattell's 16PF, enabling 16 distinct traits. It introduces PERS-16, a benchmark that adapts the MPI framework to 16PF using 163 IPIP items, and demonstrates that continuous trait intensity outperforms binary induction. To achieve robust control, the authors propose Specific Attribute Control (SAC), which uses five intensity factors (Frequency, Depth, Threshold, Effort, Willingness) and adjective-based anchoring to modulate trait expression, evaluating both SAC-Neutral and SAC-Induced states. Across four state-of-the-art LLMs and a human baseline, SAC reveals monotonic, interpretable trait deltas and coherent inter-trait co-movements, offering a path toward adaptive, context-sensitive, and psychologically grounded human-machine interactions, with future work on real-time modulation and broader validation. $\Delta_i^{(M)} = \mu_i^{\text{induced}(M)} - \mu_i^{\text{neutral}(M)}$ describes the change in trait i for model M under induction.$

Abstract

Large language models (LLMs) have gained significant traction across a wide range of fields in recent years. There is also a growing expectation for them to display human-like personalities during interactions. To meet this expectation, numerous studies have proposed methods for modelling LLM personalities through psychometric evaluations. However, most existing models face two major limitations: they rely on the Big Five (OCEAN) framework, which only provides coarse personality dimensions, and they lack mechanisms for controlling trait intensity. In this paper, we address this gap by extending the Machine Personality Inventory (MPI), which originally used the Big Five model, to incorporate the 16 Personality Factor (16PF) model, allowing expressive control over sixteen distinct traits. We also developed a structured framework known as Specific Attribute Control (SAC) for evaluating and dynamically inducing trait intensity in LLMs. Our method introduces adjective-based semantic anchoring to guide trait intensity expression and leverages behavioural questions across five intensity factors: \textit{Frequency}, \textit{Depth}, \textit{Threshold}, \textit{Effort}, and \textit{Willingness}. Through experimentation, we find that modelling intensity as a continuous spectrum yields substantially more consistent and controllable personality expression compared to binary trait toggling. Moreover, we observe that changes in target trait intensity systematically influence closely related traits in psychologically coherent directions, suggesting that LLMs internalize multi-dimensional personality structures rather than treating traits in isolation. Our work opens new pathways for controlled and nuanced human-machine interactions in domains such as healthcare, education, and interviewing processes, bringing us one step closer to truly human-like social machines.

Figures (7)

• Figure 1: Initial MPI Evaluation Prompt.
• Figure 2: P2 Evaluation Prompt.
• Figure 3: Neutral Profiling Prompt Template for SAC.
• Figure 4: Trait Intensity Induction Prompt Template
• Figure 5: Trait delta scores for Claude, GPT-4o, Gemini, Mistral across intensity levels 1, 3, and 5 using the SAC framework. At intensity 1 (top), most traits exhibit strong negative deltas, indicating a suppressed expression of the induced personality traits. At intensity 3 (middle), deltas cluster around zero, suggesting a neutral or balanced level of trait expression with early signs of co-trait movement. At intensity 5 (bottom), the target traits show strong positive deltas, reflecting pronounced and deliberate trait expression. The progression across the three plots highlights smooth, symmetric movement around the neutral baseline, showing our framework’s ability to modulate personality traits along a continuous scale with fine-grained control.