InstructUIE：面向统一信息抽取的多任务指令微调
InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
AI总结：
本文提出基于指令微调的统一信息抽取框架 InstructUIE，并构建含 32 个数据集的 IE INSTRUCTIONS 基准，在零样本设置下显著超越现有最先进方法与 GPT-3.5。
摘要：
大语言模型通过阅读指令性提示已展现出强大的多任务能力。然而，近期研究表明，现有大模型在信息抽取任务上仍存在困难。例如，gpt-3.5-turbo 在 Ontonotes 数据集上仅取得 18.22 的 F1 分数，显著低于最先进水平。本文提出 InstructUIE，一个基于指令微调的统一信息抽取框架，能够统一建模多种信息抽取任务并捕捉任务间依赖关系。为验证所提方法，我们引入 IE INSTRUCTIONS，一个包含 32 个多样化信息抽取数据集的基准，采用统一的文本到文本格式并配有专家编写的指令。实验结果表明，在有监督设置下，我们的方法达到与 Bert 相当的性能；在零样本设置下，显著优于最先进方法和 gpt3.5。
英文摘要：
Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have difficulty with information extraction tasks. For example, gpt-3.5-turbo achieved an F1 score of 18.22 on the Ontonotes dataset, which is significantly lower than the state-of-the-art performance. In this paper, we propose InstructUIE, a unified information extraction framework based on instruction tuning, which can uniformly model various information extraction tasks and capture the inter-task dependency. To validate the proposed method, we introduce IE INSTRUCTIONS, a benchmark of 32 diverse information extraction datasets in a unified text-to-text format with expert-written instructions. Experimental results demonstrate that our method achieves comparable performance to Bert in supervised settings and significantly outperforms the state-of-the-art and gpt3.5 in zero-shot settings.
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。
