Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China
Abstract
Financial and economic research often relies on structured supply-chain disclosures and commercial databases. In China, supplier--customer disclosure is typically limited to major partners of listed firms, leaving unlisted firms and long-tail inter-firm links poorly captured in structured data. Public web evidence can partly complement this gap through corporate, government, and trade-media disclosures; however, full-text web mining at scale is costly because pages are often inaccessible or expensive to process with large language models (LLMs). We propose a snippet-driven method for constructing a supply chain knowledge graph (SCKG), with firms as nodes and inter-firm relationships as edges. Web search snippets are query-biased summaries returned with search results. We use them as a scalable first-pass evidence layer for LLM-based relationship extraction. We evaluate the pipeline in terms of extraction efficiency and coverage. For extraction efficiency, exhaustive full-text chunking discovers 19.8× more unique relationships than snippets, but requires 251.2× more input tokens and yields higher redundancy. For coverage, we use 130,685 Chinese firms as search seeds, covering Shanghai/Shenzhen-listed firms and large unlisted firms as of 2024. In the listed-firm subset, the resulting SCKG covers 7.2× more firms and 9.3× more relationships than the CSMAR disclosure-based benchmark, while revealing heavy-tailed degree patterns. Retained provenance metadata make the SCKG an auditable complement to disclosure-based databases.
Versions
Related
- Crossing over universal scaling laws in two-dimensional driven dissipative condensates
- Anderson orthogonality scaling in the Rabi-driven heavy Fermi polaron
- Data-driven progressive discovery of physical laws
- Bayesian data-driven discovery of partial differential equations with variable coefficients
- Improving precision scaling via backaction-evading continuous measurement in a driven-dissipative Kerr parametric oscillator
BibTeX
@misc{fukada2026snippetdriven,
title = {{Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China}},
author = {Hiroto Fukada and Takayuki Mizuno},
howpublished = {arXiv},
year = {2026},
month = may,
doi = {10.48550/arxiv.2605.27845},
eprint = {2605.27845},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.27845},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China
AU - Hiroto Fukada
AU - Takayuki Mizuno
PY - 2026
DA - 2026/05/27
PB - arXiv
DO - 10.48550/arxiv.2605.27845
UR - https://arxiv.org/abs/2605.27845
AB - Financial and economic research often relies on structured supply-chain disclosures and commercial databases. In China, supplier--customer disclosure is typically limited to major partners of listed firms, leaving unlisted firms and long-tail inter-firm links poorly captured in structured data. Public web evidence can partly complement this gap through corporate, government, and trade-media disclosures; however, full-text web mining at scale is costly because pages are often inaccessible or expensive to process with large language models (LLMs). We propose a snippet-driven method for constructing a supply chain knowledge graph (SCKG), with firms as nodes and inter-firm relationships as edges. Web search snippets are query-biased summaries returned with search results. We use them as a scalable first-pass evidence layer for LLM-based relationship extraction. We evaluate the pipeline in terms of extraction efficiency and coverage. For extraction efficiency, exhaustive full-text chunking discovers 19.8× more unique relationships than snippets, but requires 251.2× more input tokens and yields higher redundancy. For coverage, we use 130,685 Chinese firms as search seeds, covering Shanghai/Shenzhen-listed firms and large unlisted firms as of 2024. In the listed-firm subset, the resulting SCKG covers 7.2× more firms and 9.3× more relationships than the CSMAR disclosure-based benchmark, while revealing heavy-tailed degree patterns. Retained provenance metadata make the SCKG an auditable complement to disclosure-based databases.
ER -