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

2025-06-26

AI Summary

Existing LLM-based personality modeling suffers from two key limitations: the coarse-grained nature of the Big Five framework and the lack of fine-grained control over trait intensity. This paper proposes a novel fine-grained personality modeling paradigm: (1) extending the Machine Personality Inventory (MPI) to the 16PF model, covering 16 distinct personality traits; (2) designing a continuous, semantics-anchored intensity control mechanism grounded in adjectives, dynamically modulating and evaluating trait expression along five dimensions—frequency, depth, threshold, effort, and willingness; and (3) uncovering, for the first time, the psychometrically consistent structural relationships among 16PF traits. Experimental results demonstrate significant improvements in both consistency and controllability of personality expression. This work establishes an interpretable, tunable foundation for personality modeling, enabling high-fidelity human-like interaction in applications such as healthcare companionship, personalized education, and intelligent interviewing.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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: extit{Frequency}, extit{Depth}, extit{Threshold}, extit{Effort}, and extit{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.

Problem

• Extends MPI to 16PF model for finer personality traits control
• Develops SAC framework for dynamic trait intensity evaluation
• Enables continuous spectrum modeling for consistent personality expression

Innovation

• Extends MPI with 16PF for expressive trait control
• Introduces SAC framework for dynamic intensity adjustment
• Uses adjective anchoring and five intensity factors