arXiv 2304.084602024-10-03cs.CLcs.AIcs.LG

LongForm：利用反向指令进行有效指令微调

LongForm: Effective Instruction Tuning with Reverse Instructions

Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）

Abdullatif Köksal, Timo Schick, Anna Korhonen, Hinrich Schütze

备注：: EMNLP 2024 Findings. This version extends the training with recent LLMs, evaluation with new metrics, and NLU tasks

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

LongForm通过反向指令从人类语料生成指令数据，构建LongForm-C数据集，以低成本实现有效指令微调，在长文本生成和问答任务上超越更大规模及先前微调模型。

摘要：

指令微调使语言模型能够更有效地泛化并更好地遵循用户意图。然而，获取指令数据成本高昂且具有挑战性。先前的工作采用了昂贵的人工标注、存在对齐问题的众包数据集以及通过LLM生成噪声示例等方法。我们引入了LongForm-C数据集，该数据集通过反向指令创建。我们利用反向指令，通过LLM为人类撰写的语料示例生成指令。首先，我们从C4和Wikipedia等语料库中选取多样化的人类撰写文档；然后，通过LLM为这些文档生成指令。这种方法提供了一种更廉价、更干净的指令微调数据集，其输出自然，并且适用于长文本生成。我们的模型在故事/食谱生成和长文本问答等任务上，优于未进行指令微调的10倍规模的语言模型。此外，LongForm模型大幅优于先前的指令微调模型（如FLAN-T5和Alpaca），并进一步提升了语言理解能力。我们公开发布了数据和模型：https://github.com/akoksal/LongForm。

英文摘要：

Instruction tuning enables language models to more effectively generalize and better follow user intent. However, obtaining instruction data is costly and challenging. Prior work employs methods such as expensive human annotation, crowd-sourced datasets with alignment issues, and generating noisy examples via LLMs. We introduce the LongForm-C dataset, which is created by reverse instructions. We generate instructions via LLMs for human-written corpus examples using reverse instructions. First we select a diverse set of human-written documents from corpora such as C4 and Wikipedia; then we generate instructions for these documents via LLMs. This approach provides a cheaper and cleaner instruction-tuning dataset with natural output and one suitable for long text generation. Our models outperform 10x larger language models without instruction tuning on tasks such as story/recipe generation and long-form question answering. Moreover, LongForm models outperform prior instruction-tuned models such as FLAN-T5 and Alpaca by a large margin, and improve language understanding capabilities further. We publicly release our data and models: https://github.com/akoksal/LongForm.

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。