也许仅需 0.5% 的数据：低训练数据指令微调的初步探索
Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning
AI总结：
本文探索低训练数据指令微调（LTD Instruction Tuning），发现任务专用模型仅需不到原始数据集0.5%的数据即可训练，且性能比全量数据训练提升2%，有效降低计算成本。
摘要：
大型语言模型（LLMs）的指令微调因能释放 LLMs 遵循指令的潜力而备受研究者关注。尽管指令微调作为一种微调方法有助于促进 LLMs 适应下游任务，但在大量数据上训练具有数千万甚至数十亿参数的模型会导致难以承受的计算成本。为解决此问题，我们致力于减少 LLM 指令微调中使用的数据量，以降低训练成本并提高数据效率，这被称为低训练数据指令微调（LTD Instruction Tuning）。具体而言，本文对减少 LLM 训练中使用的数据进行了初步探索，并得出了关于 LLM 训练任务专业化的若干观察，例如特定任务性能的优化、指令微调所需的指令类型数量，以及任务专用模型所需的数据量。结果表明，任务专用模型可使用不到原始数据集 0.5% 的数据进行训练，且性能比在全量任务相关数据上训练的模型提升 2%。
英文摘要：
Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the adaptation of large language models (LLMs) to downstream tasks as a fine-tuning approach, training models with tens of millions or even billions of parameters on large amounts of data results in unaffordable computational costs. To address this, we focus on reducing the data used in LLM instruction tuning to decrease training costs and improve data efficiency, dubbed as Low Training Data Instruction Tuning (LTD Instruction Tuning). Specifically, this paper conducts a preliminary exploration into reducing the data used in LLM training and identifies several observations regarding task specialization for LLM training, such as the optimization of performance for a specific task, the number of instruction types required for instruction tuning, and the amount of data required for task-specific models. The results suggest that task-specific models can be trained using less than 0.5% of the original dataset, with a 2% improvement in performance over those trained on full task-related data.
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。
