Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits

TL;DR

Orca is a framework that enhances large language models' role-playing abilities by integrating personality traits through data augmentation, specialized training, and a new benchmark for evaluating social content generation.

Contribution

The paper introduces Orca, a novel framework for inferring, augmenting, and training LLMs with personality traits to improve role-playing, along with a new benchmark for evaluation.

Findings

Orca outperforms existing models on the new benchmark.

Integrating personality traits improves role-playing quality.

The framework effectively perceives and utilizes personality information.

Abstract

Large language models has catalyzed the development of personalized dialogue systems, numerous role-playing conversational agents have emerged. While previous research predominantly focused on enhancing the model's capability to follow instructions by designing character profiles, neglecting the psychological factors that drive human conversations. In this paper, we propose Orca, a framework for data processing and training LLMs of custom characters by integrating personality traits. Orca comprises four stages: (1) Personality traits inferring, leverage LLMs to infer user's BigFive personality trait reports and scores. (2) Data Augment, simulate user's profile, background story, and psychological activities. (3) Dataset construction, personality-conditioned instruction prompting (PCIP) to stimulate LLMs. (4) Modeling and Training, personality-conditioned instruction tuning (PTIT and PSIT), using the generated data to enhance existing open-source LLMs. We introduce OrcaBench, the first benchmark for evaluating the quality of content generated by LLMs on social platforms across multiple scales. Our experiments demonstrate that our proposed model achieves superior performance on this benchmark, demonstrating its excellence and effectiveness in perceiving personality traits that significantly improve role-playing abilities. Our Code is available at https://github.com/Aipura/Orca.