Research /
Evaluation of Large Language Models for Determining Requirement Consistency ↗
This study benchmarks various LLMs in assessing the consistency of engineering requirements for spacecraft subsystems.
Research & notes
Questions worth investigating.
Studies of AI and engineering, with methods, results, and limitations. Explore the thinking behind the work.
Subscribe via RSS ↗Research /
Evaluating Large Language Models for Satellite Conjunction Email Analysis ↗
This paper benchmarks LLMs for automating satellite conjunction email analysis, assessing classification and extraction performance.