Faithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge Graphs
Quick Answer
This paper shows that An automated LLM-driven pipeline converts hardware datasheets into hierarchical knowledge graphs, achieving 98.8% property faithfulness and covering 83.6% of baseline properties, significantly improving engineering information reliability for hardware design and verification.
Key Points
- Framework uses chunk-based extraction and iterative refinement for knowledge graph creation.
- Achieves 98.8% property faithfulness compared to 76.1% for one-shot processing.
- Covers 83.6% of properties from the baseline, while the baseline covers only 10.5% of new properties.
- Reduces risk of overlooked constraints in hardware design and verification.
- Evaluated on 20 diverse hardware datasheets for comprehensive performance.
DeepSignal Analysis
What happened
A new automated pipeline utilizes large language models (LLMs) to convert hardware datasheets into hierarchical knowledge graphs. This method reportedly achieves 98.8% property faithfulness and covers 83.6% of baseline properties, significantly enhancing the reliability of engineering information for hardware design.
Key evidence
- The automated pipeline transforms hardware datasheets into hierarchical knowledge graphs using chunk-based property extraction and iterative refinement.
- The framework achieves 98.8% property faithfulness compared to 76.1% for a one-shot baseline, indicating a substantial improvement in accuracy.
- The evaluation involved 20 hardware datasheets of varying types and lengths, demonstrating the method's applicability across diverse documents.
Why it matters
The ability to automate the extraction and organization of information from hardware datasheets can reduce human error and improve the efficiency of hardware design processes. By achieving high property faithfulness and comprehensive coverage, this approach may help engineers make better-informed decisions, minimizing the risk of overlooking critical specifications.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual inspection is tedious and error-prone because datasheets are lengthy and heterogeneous, with dense information fragmented across tables, figures, and text. Although large language models (LLMs) can automate this process, naïve one-shot processing omits relevant specifications even when the document fits within the model's context window.
We present an automated LLM-driven pipeline that transforms hardware datasheets into general-purpose hierarchical hardware knowledge graphs through chunk-based property extraction, hierarchical routing, and iterative refinement. The framework uses LLMs for information extraction and semantic reasoning while preserving source provenance and applying graph updates through validated instructions and deterministic local execution. This staged design reduces per-query context and maintains traceable intermediate representations. The resulting knowledge graphs provide semantically organized, source-grounded hardware properties for downstream retrieval and reasoning.
We evaluate the framework on 20 hardware datasheets spanning diverse component types and document lengths. We assess property faithfulness and introduce inter-graph completeness to measure relative semantic coverage without exhaustive ground truth. Our framework achieves 98.8% property faithfulness compared with 76.1% for the one-shot baseline, while fully covering 83.6% of faithful baseline properties; in the reverse direction, the baseline fully covers only 10.5% of ours. These improvements provide more reliable and comprehensive engineering information for downstream hardware design and verification, reducing the risk of overlooked constraints and incorrect decisions.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12762 [cs.AI] |
| (or arXiv:2610.12762v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12762 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haotian Qiao [view email]
[v1]
Thu, 8 Oct 2026 22:12:37 UTC (2,258 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →VEPA: Verified Evolving Formal Policy for Lifelong Agent Guardrails
VEPA introduces a framework for verified evolving formal policies for LLM agents, enhancing safety by adapting guardrails based on deployment feedback. It outperforms existing methods across benchmarks like ASSEBench-Safety and ASSEBench-Security, ensuring deterministic policy enforcement even under challenging conditions.