LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval

TL;DR

LogosKG is a hardware-efficient framework for scalable, interpretable multi-hop knowledge graph retrieval that enhances KG-LLM integration and biomedical reasoning.

Contribution

It introduces a hardware-aligned, scalable retrieval method using symbolic formulations and efficient traversal operations for large knowledge graphs.

Findings

Achieves substantial efficiency gains over CPU and GPU baselines.

Maintains retrieval fidelity while scaling to billion-edge graphs.

Enables evidence-grounded biomedical reasoning with large KGs.

Abstract

Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop retrieval, yet existing systems struggle to balance efficiency, scalability, and interpretability. We introduce LogosKG, a novel, hardware-aligned framework that enables scalable and interpretable k-hop retrieval on large KGs by building on symbolic KG formulations and executing traversal as hardware-efficient operations over decomposed subject, object, and relation representations. To scale to billion-edge graphs, LogosKG integrates degree-aware partitioning, cross-graph routing, and on-demand caching. Experiments show substantial efficiency gains over CPU and GPU baselines without loss of retrieval fidelity. With proven performance in KG retrieval, a downstream two-round KG-LLM interaction demonstrates how LogosKG enables large-scale, evidence-grounded analysis of how KG topology, such as hop distribution and connectivity, shapes the alignment between structured biomedical knowledge and LLM diagnostic reasoning, thereby opening the door for next-generation KG-LLM integration. The source code is publicly available at https://github.com/LARK-NLP-Lab/LogosKG, and an online demo is available at https://lark-nlp-lab-logoskg.hf.space/.