LIMIT：跨评估范式的指令微调中“少即是多”
LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms
AI总结：
本研究探究指令微调中数据规模与多样性的影响，发现1k-6k条样本足以在传统NLP基准和基于模型的评估上取得良好性能，且混合教科书式与开放式问答数据可优化两种范式下的表现。
摘要：
大型语言模型传统上在大规模指令数据集上进行微调。然而，近期研究表明，小型但高质量的数据集可能足以实现通用指令遵循。围绕微调最佳实践的共识缺失，部分原因在于LLM评估方法的快速分化。在本研究中，我们探讨少量多样化的微调样本是否能同时提升基于困惑度的传统NLP基准和开放式、基于模型的评估的性能。我们在规模从1k到60k样本不等的指令微调数据集上微调了开源的MPT-7B和MPT-30B模型。我们发现，1k-6k条指令微调样本的子集足以在（1）传统NLP基准和（2）基于模型的评估上均取得良好性能。最后，我们表明，混合教科书式与开放式问答微调数据集能在两种评估范式上优化性能。
英文摘要：
Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding finetuning best practices is in part due to rapidly diverging approaches to LLM evaluation. In this study, we ask whether a small amount of diverse finetuning samples can improve performance on both traditional perplexity-based NLP benchmarks, and on open-ended, model-based evaluation. We finetune open-source MPT-7B and MPT-30B models on instruction finetuning datasets of various sizes ranging from 1k to 60k samples. We find that subsets of 1k-6k instruction finetuning samples are sufficient to achieve good performance on both (1) traditional NLP benchmarks and (2) model-based evaluation. Finally, we show that mixing textbook-style and open-ended QA finetuning datasets optimizes performance on both evaluation paradigms.
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。
