Abstract
Answering complex logical queries over incomplete knowledge graphs (KGs) is challenging. 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 logical reasoning schema over knowledge graphs 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. Our code and model will be released at GitHub and huggingface soon.
Abstract (translated)
回答复杂逻辑查询在半完整知识图(KG)上具有挑战性。大多数先前的研究都专注于学习实体/关系嵌入和用各种神经网络模拟第一范式逻辑操作。然而,它们因无法共享世界知识来提高逻辑推理能力而陷入瓶颈,从而导致性能较低。在本文中,我们提出了一种在大型语言模型(LLMs)上的复杂逻辑推理模式,包含一个基于课程的逻辑感知指令调整框架,称为LACT。具体来说,我们通过二叉树分解来增强任意第一范式逻辑查询,以刺激LLMs的推理能力。为了解决不同类型复杂查询之间的困难差距,我们设计了一个简单而灵活的逻辑感知课程学习框架。在广泛使用数据集上的实验证明,LACT在先进方法上取得了很大的改进(将平均+5.5%的MRR得分)实现了一种新的最优状态。我们的代码和模型将在GitHub和huggingface不久后发布。
URL
https://arxiv.org/abs/2405.01649