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

arXiv:2405.01649v1 Announce Type: new
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 …

abstract arxiv cs.cl curriculum embeddings graph graphs however improving knowledge knowledge graph knowledge graphs logic networks neural networks operators queries reasoning type world