Graph-DPEP：基于思维图推理的小样本文档关系抽取的分解式即插即用集成方法
Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning
AI总结：
本文提出Graph-DPEP框架，通过分解式即插和集成式玩法，利用思维图推理，解决小样本文档级关系抽取中结构化输出转换和关系类型区分难题，在公开基准上表现优越。
摘要：
在大型语料库上预训练的大型语言模型（LLMs）在许多NLP任务上展现出了令人印象深刻的小样本学习能力。将NLP任务重构为文本到文本的生成任务是常见做法，以便生成式LLMs可以被提示来解决该任务。然而，由于DocRE的结构化输出格式使得转换为纯文本变得复杂，使用生成式LLM模型执行文档级关系抽取（DocRE）任务仍然具有挑战性。小样本样本和提示指令中可用的有限信息进一步增加了文档中提及实体间关系抽取的难度和挑战。在本文中，我们将结构化输出表示为图风格的三元组而非自然语言表达，并利用生成式LLMs处理DocRE任务。我们的方法，即Graph-DPEP框架，基于以自然语言呈现的三元组解释思维背后的推理。在该框架中，我们首先引入一种“分解式即插”方法，通过类型空间分解在提示上执行LLMs的生成，以减轻区分所有关系类型的负担。其次，我们采用验证器来校准生成并识别被忽略的查询实体对。第三，我们开发了“集成式玩法”，通过利用与缺失查询对关联的子图中嵌入的推理思维，重新在完整类型列表上应用生成，以解决缺失问题。通过与现有提示技术和替代语言模型（LLMs）的广泛比较，我们的框架在实验中于公开可用的基准上展示了优越的性能。
英文摘要：
Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning capability on many NLP tasks. Recasting an NLP task into a text-to-text generation task is a common practice so that generative LLMs can be prompted to resolve it. However, performing document-level relation extraction (DocRE) tasks with generative LLM models is still challenging due to the structured output format of DocRE, which complicates the conversion to plain text. Limited information available in few-shot samples and prompt instructions induce further difficulties and challenges in relation extraction for mentioned entities in a document. In this paper, we represent the structured output as a graph-style triplet rather than natural language expressions and leverage generative LLMs for the DocRE task. Our approach, the Graph-DPEP framework is grounded in the reasoning behind triplet explanation thoughts presented in natural language. In this framework, we first introduce a ``decomposed-plug" method for performing the generation from LLMs over prompts with type-space decomposition to alleviate the burden of distinguishing all relation types. Second, we employ a verifier for calibrating the generation and identifying overlooked query entity pairs. Third, we develop "ensemble-play", reapplying generation on the entire type list by leveraging the reasoning thoughts embedded in a sub-graph associated with the missing query pair to address the missingness issue. Through extensive comparisons with existing prompt techniques and alternative Language Models (LLMs), our framework demonstrates superior performance on publicly available benchmarks in experiments.
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。
