Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
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.
Code (1)
Tasks
Incremental LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Diffusion-Driven Fine-Grained Nodule Synthesis Framework for Enhanced Lung Nodule Detection from Chest Radiographs
Early detection of lung cancer in chest radiographs (CXRs) is crucial for improving patient outcomes, yet nodule detection remains challenging due to their subtle appearance and variability in radiological characteristic…
Synthetic Data GenerationLung Nodule DetectionLeveraging Google Earth Engine platform to characterize and map small seasonal wetlands in the semi-arid environments of South Africa
Small seasonal wetlands are a distinctive feature of the semi-arid environments. Although these systems are small and ephemeral in nature, they provide habitats to aquatic flora and fauna, and play a critical role in sus…
ManagementDLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models
Recent advancements in Large Language Models (LLMs) have achieved robust performance across diverse tasks, but fine-tuning these models for specific domains remains resource-intensive. Parameter-Efficient Fine-Tuning (PE…
Multiple-choiceparameter-efficient fine-tuningQuestion AnsweringSentenceWhen pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models
Pre-training on a source task is usually expected to facilitate fine-tuning on similar downstream problems. In this work, we mathematically show that this naive intuition is not always true: excessive pre-training can co…
TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition
While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls short, especially in multidimensional task scenarios. To …
GPUMulti-Task Learningparameter-efficient fine-tuningVisual Question Answering