arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.01649cs.CL
收藏

基于逻辑感知课程调优改进知识图谱上的复杂推理

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

Wuhan University(武汉大学);The University of Sydney(悉尼大学);JD Explore Academy(京东探索研究院);Nanyang Technological University(南洋理工大学)

Tianle Xia, Liang Ding, Guojia Wan, Yibing Zhan, Bo Du, Dacheng Tao

AI总结:

本文提出基于大语言模型的逻辑感知课程调优框架LACT,通过二叉树分解增强一阶逻辑查询,并引入课程学习解决复杂查询难度差异,在多个数据集上实现平均+5.5% MRR提升,达到最先进水平。

摘要:

在不完整的知识图谱(KGs)上回答复杂查询是一项具有挑战性的工作。以往的大多数工作集中在学习实体/关系嵌入,并用各种神经网络模拟一阶逻辑算子。然而,它们受限于无法共享世界知识以改善逻辑推理,从而导致次优性能。在本文中,我们在大语言模型(LLMs)之上提出了一种基于KG的复杂推理模式,包含一个基于课程的逻辑感知指令调优框架,命名为LACT。具体而言,我们通过二叉树分解来增强任意一阶逻辑查询,以激发LLMs的推理能力。为了解决不同类型复杂查询之间的难度差异,我们设计了一个简单且灵活的逻辑感知课程学习框架。在广泛使用的数据集上的实验表明,LACT相比先进方法有显著改进(带来平均+5.5%的MRR分数),达到了新的最先进水平。

英文摘要:

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements~(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.

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。

↑