Saved in:
| Main Authors: | , , , |
|---|---|
| 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!
|
| _version_ | 1866910017716748288 |
|---|---|
| author | Srun, Nalin Rastin, Parisa Cabanes, Guénaël Assala, Lydia Boudjeloud |
| author_facet | Srun, Nalin Rastin, Parisa Cabanes, Guénaël Assala, Lydia Boudjeloud |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09624 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MILE-RefHumEval: A Reference-Free, Multi-Independent LLM Framework for Human-Aligned Evaluation Srun, Nalin Rastin, Parisa Cabanes, Guénaël Assala, Lydia Boudjeloud Computation and Language 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. |
| title | MILE-RefHumEval: A Reference-Free, Multi-Independent LLM Framework for Human-Aligned Evaluation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.09624 |