LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914494243930112 |
|---|---|
| author | Cheng, He Wu, Yifu Khatwani, Saksham Kruse, Maya Dligach, Dmitriy Miller, Timothy A. Afshar, Majid Gao, Yanjun |
| author_facet | Cheng, He Wu, Yifu Khatwani, Saksham Kruse, Maya Dligach, Dmitriy Miller, Timothy A. Afshar, Majid Gao, Yanjun |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18913 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval Cheng, He Wu, Yifu Khatwani, Saksham Kruse, Maya Dligach, Dmitriy Miller, Timothy A. Afshar, Majid Gao, Yanjun Computation and Language 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/. |
| title | LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.18913 |