上下文学习与指令微调:小语言模型和多语言情况的案例
In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models
AI总结:
研究评估了上下文学习在非英语语言和不同模型大小下的指令遵循有效性,发现其表现下降,但通过直接偏好优化可部分提升性能。
摘要:
指令遵循是大语言模型执行下游任务的关键能力。传统的指令微调方法依赖于在经过整理的指令数据集上进行监督微调,可选地补充以人类偏好的对齐步骤。最近的研究显示,上下文学习(ICL)替代方法可以引导基础模型向指令遵循发展。这种类型的方法尤其相关于避免监督指令微调所需的显著努力和资源。在本工作中,我们评估了在特别相关的情况下(即非英语语言和不同模型大小)上下文学习用于指令遵循的可行性。我们的结果表明,这些情况导致上下文学习指令遵循性能下降。我们进一步表明,对基础模型应用直接偏好优化可以部分提高基准结果,尽管当前的上下文学习指令遵循方法需要替代方案来弥补与以英语为中心的大型语言模型之间的差距。
英文摘要:
Instruction following is a critical ability for Large Language Models to be used directly by humans. This often requires supervised fine-tuning on curated instruction datasets, sometimes complemented with an alignment step. However, in multilingual scenarios, obtaining high-quality data for these stages remains challenging, motivating the exploration of In-Context Learning (ICL) as a possible alternative. In this work, we study whether ICL can serve as a substitute for Instruction Tuning in multilingual language models, while also examining how the comparison changes with model scale. Our results indicate that a gap remains between ICL and Instruction Tuning, motivating further research to reduce it.
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。