Neuron-based Personality Trait Induction in Large Language Models

TL;DR

This paper introduces a neuron-based method for inducing specific personality traits in large language models, using a new dataset and neuron manipulation techniques to achieve trait control without retraining.

Contribution

It presents a novel neuron identification and manipulation approach for personality trait induction in LLMs, grounded in a large-scale psychological dataset.

Findings

Effective neuron-based trait induction comparable to fine-tuning

Efficient method requires no model retraining

Resources and dataset publicly available

Abstract

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 is 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. This method enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validate 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. We provide access to all the mentioned resources at https://github.com/RUCAIBox/NPTI.