Conference
Open access
Jul 2026
Human-Grounded Evaluation of Large Language Models for Optical Network Automation
This work presents HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set of expert ratings to enable scalable and reproducible comparison of candidate LLMs, and to rank them using a quality efficiency score (QES).
Kiarash Rezaei, Omran Ayoub, P. Monti et al.
· International Conference on... · 0 citations