LLMs systematically map semiconductor supply chain risks from corporate disclosures

Researchers have developed an end-to-end system to extract and prioritize risk intelligence from public corporate disclosures within the semiconductor industry. This pipeline utilizes large language models (LLMs) to identify and categorize risks and opportunities described in company documents, organizing them into a knowledge graph. The system then merges duplicates and ranks them using a multi-layered approach involving an algorithmic formula, LLM adjustments, and expert validation. Applied to five semiconductor companies, the system generated over 76,000 scored items, with an independent check confirming the validity of 92.6% of them. AI

IMPACT This research demonstrates a novel application of LLMs for systematic risk assessment in critical supply chains, potentially improving strategic planning for industries.

RANK_REASON This is a research paper detailing a new methodology for risk analysis using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• Alexander Fichtl M.Sc.
• alphaXiv
• arXiv
• CatalyzeX
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• large language models
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →