用大模型自动发现新关系，无需人工标注。
LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models
- 基于大模型示范生成新关系，跳过传统聚类与人工标注。
- 在三个数据集上准确率最高达78.3%，显著优于基线方法。
- 适合需要快速拓展关系抽取能力的开发者和研究者。
开放关系抽取（OpenRE）的目标是构建可泛化到训练中未见新关系的抽取模型。现有方法多将OpenRE视为聚类任务：先根据实例相似性聚类，再人工为每类分配新关系，但依赖人工标注限制了实用性。本文提出基于大语言模型（LLM）的OpenRE框架LLM-OREF，直接利用模型的语言理解与生成能力，无需人工干预即可为测试实例预测新关系。框架包含两个核心组件：(1) 关系发现器（RD），基于训练实例的示范预测测试实例的新关系；(2) 关系预测器（RP），从n个候选关系中为测试实例选择最可能的关系，由示范实例引导。为提升预测性能，设计三阶段自校正推理策略：首先由RD初步预测所有测试实例关系；其次通过交叉验证筛选高置信度实例构成可靠示范；最后基于这些可靠示范重新预测所有实例关系。在三个OpenRE数据集上的实验表明，该框架有效。代码已开源：https://github.com/XMUDeepLIT/LLM-OREF.git。
原文摘要 · Abstract (English)
The goal of open relation extraction (OpenRE) is to develop an RE model that can generalize to new relations not encountered during training. Existing studies primarily formulate OpenRE as a clustering task. They first cluster all test instances based on the similarity between the instances, and then manually assign a new relation to each cluster. However, their reliance on human annotation limits their practicality. In this paper, we propose an OpenRE framework based on large language models (LLMs), which directly predicts new relations for test instances by leveraging their strong language understanding and generation abilities, without human intervention. Specifically, our framework consists of two core components: (1) a relation discoverer (RD), designed to predict new relations for test instances based on \textit{demonstrations} formed by training instances with known relations; and (2) a relation predictor (RP), used to select the most likely relation for a test instance from $n$ candidate relations, guided by \textit{demonstrations} composed of their instances. To enhance the ability of our framework to predict new relations, we design a self-correcting inference strategy composed of three stages: relation discovery, relation denoising, and relation prediction. In the first stage, we use RD to preliminarily predict new relations for all test instances. Next, we apply RP to select some high-reliability test instances for each new relation from the prediction results of RD through a cross-validation method. During the third stage, we employ RP to re-predict the relations of all test instances based on the demonstrations constructed from these reliable test instances. Extensive experiments on three OpenRE datasets demonstrate the effectiveness of our framework. We release our code at https://github.com/XMUDeepLIT/LLM-OREF.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。