Search papers, labs, and topics across Lattice.
LogosKG is introduced as a hardware-aligned framework for scalable and interpretable k-hop retrieval on large knowledge graphs, using symbolic KG formulations and decomposed subject, object, and relation representations. It incorporates degree-aware partitioning, cross-graph routing, and on-demand caching to scale to billion-edge graphs. Experiments demonstrate significant efficiency improvements over CPU and GPU baselines, and a downstream KG-LLM interaction showcases evidence-grounded analysis of KG topology's impact on LLM reasoning.
Forget slow, uninterpretable KG lookups: LogosKG unlocks interactive, billion-edge knowledge graph retrieval with orders-of-magnitude speedups by compiling symbolic queries to hardware-optimized operations.
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/.
