This work introduces LAB (Large-scale Alignment for chatBots), a novel methodology designed to overcome the scalability challenges in the instruction-tuning phase of large language model (LLM) training. Leveraging a taxonomy-guided synthetic data generation process and a multi-phase tuning framework, LAB significantly reduces reliance on expensive human annotations and proprietary models like GPT-4. We demonstrate that LAB-trained models can achieve competitive performance across several benchmarks compared to models trained with traditional human-annotated or GPT-4 generated synthetic data. Thus offering a scalable, cost-effective solution for enhancing LLM capabilities and instruction-following behaviors without the drawbacks of catastrophic forgetting, marking a step forward in the efficient training of LLMs for a wide range of applications.

翻译：本文提出LAB（Large-scale Alignment for chatBots，面向聊天机器人的大规模对齐方法）——一种旨在克服大语言模型（LLM）训练中指令微调阶段扩展性挑战的新型方法论。通过利用基于分类学指导的合成数据生成流程与多阶段微调框架，LAB显著降低了对昂贵人工标注及GPT-4等专有模型的依赖。实验证明，相较于使用传统人工标注或GPT-4生成的合成数据训练的模型，经LAB训练的模型在多项基准测试中均能达到具有竞争力的性能表现。该方法在避免灾难性遗忘缺陷的同时，为增强LLM能力与指令遵循行为提供了可扩展、低成本的解决方案，标志着面向广泛领域应用的高效LLM训练迈出了重要一步。