LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval

ACL ARR 2026 January Submission7675 Authors

Keywords: Knowledge graphs; neurosymbolic approaches; information Retrieval and Text Mining; biomedical knowledge graphs; clinical NLP

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.

Paper Type: Long

Research Area: Low-resource Methods for NLP

Research Area Keywords: NLP in resource-constrained settings, knowledge graphs, clinical NLP

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 7675