Saved in:
Bibliographic Details
Main Authors: Srun, Nalin, Rastin, Parisa, Cabanes, Guénaël, Assala, Lydia Boudjeloud
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.09624
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We introduce MILE-RefHumEval, a reference-free framework for evaluating Large Language Models (LLMs) without ground-truth annotations or evaluator coordination. It leverages an ensemble of independently prompted evaluators guided by a human-aligned schema, supporting both discrete and continuous scoring judgement. With task-specific prompts from best candidate selection, summarization and image captioning to dialogue, MILE-RefHumEval provides flexible, interpretable, and scalable assessments. Experiments show it aligns closely with human judgments, outperforms prior methods, and reduces computational overhead, offering an efficient, robust, and human-aligned solution for real-world LLM evaluation.