Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
This addresses the problem of efficient multi-character imitation in dialogue agents for users seeking engaging interactions, though it appears incremental as it builds on existing LoRA techniques.
The paper tackles the challenge of multi-character role-playing with LLMs by introducing Neeko, a framework that uses dynamic LoRA adapters to adapt to diverse characters, resulting in superior performance over existing methods.
Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character role-playing (MCRP) scenarios. To address the issue, we present Neeko, an innovative framework designed for efficient multiple characters imitation. Unlike existing methods, Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters. Our framework breaks down the role-playing process into agent pre-training, multiple characters playing, and character incremental learning, effectively handling both seen and unseen roles. This dynamic approach, coupled with distinct LoRA blocks for each character, enhances Neeko's adaptability to unique attributes, personalities, and speaking patterns. As a result, Neeko demonstrates superior performance in MCRP over most existing methods, offering more engaging and versatile user interaction experiences. Code and data are available at https://github.com/weiyifan1023/Neeko.