CITB：一个用于持续指令微调的基准
CITB: A Benchmark for Continual Instruction Tuning
AI总结：
本文提出了持续指令微调（CIT）基准，通过构建学习和评估协议及两种长对话任务流，系统研究现有持续学习方法在指令微调中的表现，发现顺序微调指令模型效果相当或更优。
摘要：
持续学习（CL）是一种旨在复制人类持续学习和积累知识的能力而不遗忘先前知识并将其迁移到新任务的范式。近期的指令微调（IT）涉及对模型进行微调，使其更普遍地适应解决NLP任务。然而，指令微调在CL任务语境下如何运作仍不确定。这个具有挑战性但实用的问题被表述为持续指令微调（CIT）。在这项工作中，我们建立了一个由学习和评估协议组成的CIT基准。我们策划了两种不同类型的长对话任务流，InstrDialog和InstrDialog++，以系统地研究各种CL方法。我们的实验表明，现有的CL方法未能有效利用丰富的自然语言指令，并且顺序地微调一个经过指令微调的模型可以产生相似或更好的结果。我们进一步探索了可能影响CIT学习的不同方面。我们希望这个基准将促进这一方向的更多研究。
英文摘要：
Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves fine-tuning models to make them more adaptable to solving NLP tasks in general. However, it is still uncertain how instruction tuning works in the context of CL tasks. This challenging yet practical problem is formulated as Continual Instruction Tuning (CIT). In this work, we establish a CIT benchmark consisting of learning and evaluation protocols. We curate two long dialogue task streams of different types, InstrDialog and InstrDialog++, to study various CL methods systematically. Our experiments show that existing CL methods do not effectively leverage the rich natural language instructions, and fine-tuning an instruction-tuned model sequentially can yield similar or better results. We further explore different aspects that might affect the learning of CIT. We hope this benchmark will facilitate more research in this direction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
