Go to ICLR 2025 Conference homepageNeuron based Personality Trait Induction in Large Language Models
Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PERSONALITYBENCH, a large-scale dataset for identifying and evaluating personality traits in LLMs. This dataset is grounded in the Big Five personality traits from psychology and designed to assess the generative capabilities of LLMs towards specific personality traits. Second, by leveraging PERSONALITYBENCH, we propose an efficient method for identifying personality-related neurons within LLMs by examining the opposite aspects of a given trait. Third, we develop a simple yet effective induction method that manipulates the values of these identified personality-related neurons, which enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validates the efficacy of our neuron identification and trait induction methods. Notably, our approach achieves comparable performance as fine-tuned models, offering a more efficient and flexible solution for personality trait induction in LLMs.