Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models (LLMs). However, achieving the right balance of data is crucial to prevent catastrophic forgetting and interference between tasks. To address these limitations and enhance training flexibility, we propose the Mixture-of-LoRAs (MoA) architecture which is a novel and parameter-efficient tuning method designed for multi-task learning with LLMs. In this paper, we start by individually training multiple domain-specific LoRA modules using corresponding supervised corpus data. These LoRA modules can be aligned with the expert design principles observed in Mixture-of-Experts (MoE). Subsequently, we combine the multiple LoRAs using an explicit routing strategy and introduce domain labels to facilitate multi-task learning, which help prevent interference between tasks and ultimately enhances the performance of each individual task. Furthermore, each LoRA model can be iteratively adapted to a new domain, allowing for quick domain-specific adaptation. Experiments on diverse tasks demonstrate superior and robust performance, which can further promote the wide application of domain-specific LLMs.

使用Mixture-of-LoRAs (MoA)架构的多任务学习方法，通过培训多个领域特定的LoRA模块，采用明确的路由策略和领域标签来防止任务之间的干扰，并最终提高每个个体任务的性能，进而促进领域特定大语言模型（LLMs）的广泛应用。

混合LoRA：大型语言模型的高效多任务调优