Technology Mapping with Large Language Models
This provides a more accurate solution for businesses needing insights into technology stacks for partnerships and strategy, though it appears incremental as it builds on existing LLM and semantic methods.
The authors tackled the problem of technology mapping from unstructured data by developing STARS, a framework using Large Language Models and Sentence-BERT, which significantly improved retrieval accuracy for identifying and ranking corporate technologies.
In today's fast-evolving business landscape, having insight into the technology stacks that organizations use is crucial for forging partnerships, uncovering market openings, and informing strategic choices. However, conventional technology mapping, which typically hinges on keyword searches, struggles with the sheer scale and variety of data available, often failing to capture nascent technologies. To overcome these hurdles, we present STARS (Semantic Technology and Retrieval System), a novel framework that harnesses Large Language Models (LLMs) and Sentence-BERT to pinpoint relevant technologies within unstructured content, build comprehensive company profiles, and rank each firm's technologies according to their operational importance. By integrating entity extraction with Chain-of-Thought prompting and employing semantic ranking, STARS provides a precise method for mapping corporate technology portfolios. Experimental results show that STARS markedly boosts retrieval accuracy, offering a versatile and high-performance solution for cross-industry technology mapping.