AgentRE:一种面向关系抽取中复杂信息场景的智能体框架
AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction
AI总结:
本文提出基于智能体的关系抽取框架AgentRE,利用大语言模型的记忆、检索与反思能力应对复杂场景,并通过轨迹精炼构建高质量训练数据以微调小模型,在低资源场景下表现优越。
摘要:
复杂场景下的关系抽取面临关系类型多样、单句内实体关系模糊等挑战,导致纯“文本输入-文本输出”语言模型性能不佳。为应对这些挑战,本文提出一种基于智能体的关系抽取框架AgentRE,充分利用大语言模型(LLMs)的记忆、检索与反思能力,在复杂场景中实现关系抽取。具体而言,AgentRE构建了三个主要模块,作为帮助智能体获取和处理各类有用信息的工具,从而提升关系抽取性能。我们在英文和中文两个数据集上的大量实验结果表明,AgentRE具有优越的性能,尤其在低资源场景下表现突出。此外,AgentRE生成的轨迹可以经过精炼,构建包含不同推理方法的高质量训练数据集,用于微调更小的模型。代码见https://github.com/Lightblues/AgentRE。
英文摘要:
The relation extraction (RE) in complex scenarios faces challenges such as diverse relation types and ambiguous relations between entities within a single sentence, leading to the poor performance of pure "text-in, text-out" language models (LMs). To address these challenges, in this paper, we propose an agent-based RE framework, namely AgentRE, which fully leverages the potential of large language models (LLMs) including memory, retrieval and reflection, to achieve RE in complex scenarios. Specifically, three major modules are built in AgentRE serving as the tools to help the agent acquire and process various useful information, thereby obtaining improved RE performance. Our extensive experimental results upon two datasets in English and Chinese demonstrate our AgentRE's superior performance, especially in low-resource scenarios. Additionally, the trajectories generated by AgentRE can be refined to construct a high-quality training dataset incorporating different reasoning methods, which can be used to fine-tune smaller models. Code is available at https://github.com/Lightblues/AgentRE.
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。