指令与抽取：面向按需信息抽取的指令微调
Instruct and Extract: Instruction Tuning for On-Demand Information Extraction
AI总结：
针对非专家用户的长尾临时信息抽取需求，提出按需信息抽取新范式，构建InstructIE基准并开发ODIE模型，显著优于同等规模开源模型。
摘要：
具备指令跟随能力的大语言模型向更广泛的用户群体敞开了大门。然而，在信息抽取这一自然语言处理的经典任务中，大多数特定任务系统无法很好地适应非专家用户的长尾临时抽取场景。为了解决这一问题，我们提出了一种名为按需信息抽取的新范式，以满足真实世界用户的个性化需求。该任务旨在遵循指令，从相关文本中抽取所需内容，并以结构化的表格形式呈现。表头可以由用户指定，也可以由模型根据上下文推断得出。为了促进这一新兴领域的研究，我们提出了一个名为InstructIE的基准，其中包含自动生成的训练数据以及人工标注的测试集。基于InstructIE，我们进一步开发了一个按需信息抽取器，即ODIE。在我们的基准上的综合评估表明，ODIE显著优于同等规模的现有开源模型。我们的代码和数据集已发布于https://github.com/yzjiao/On-Demand-IE。
英文摘要：
Large language models with instruction-following capabilities open the door to a wider group of users. However, when it comes to information extraction - a classic task in natural language processing - most task-specific systems cannot align well with long-tail ad hoc extraction use cases for non-expert users. To address this, we propose a novel paradigm, termed On-Demand Information Extraction, to fulfill the personalized demands of real-world users. Our task aims to follow the instructions to extract the desired content from the associated text and present it in a structured tabular format. The table headers can either be user-specified or inferred contextually by the model. To facilitate research in this emerging area, we present a benchmark named InstructIE, inclusive of both automatically generated training data, as well as the human-annotated test set. Building on InstructIE, we further develop an On-Demand Information Extractor, ODIE. Comprehensive evaluations on our benchmark reveal that ODIE substantially outperforms the existing open-source models of similar size. Our code and dataset are released on https://github.com/yzjiao/On-Demand-IE.
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。
