Ranking Large Language Models without Ground Truth

Amit Dhurandhar, Rahul Nair, Moninder Singh, Elizabeth Daly, Karthikeyan Natesan Ramamurthy


Abstract
Evaluation and ranking of large language models (LLMs) has become an important problem with the proliferation of these models and their impact. Evaluation methods either require human responses which are expensive to acquire or use pairs of LLMs to evaluate each other which can be unreliable. In this paper, we provide a novel perspective where, given a dataset of prompts (viz. questions, instructions, etc.) and a set of LLMs, we rank them without access to any ground truth or reference responses. Inspired by real life where both an expert and a knowledgeable person can identify a novice our main idea is to consider triplets of models, where each one of them evaluates the other two, correctly identifying the worst model in the triplet with high probability. We also analyze our idea and provide sufficient conditions for it to succeed. Applying this idea repeatedly we propose two methods to rank LLMs. In experiments on different generative tasks (summarization, multiple-choice, and dialog), our methods reliably recover true rankings without reference data. This points to a viable low-resource mechanism for practical use.
Anthology ID:
2024.findings-acl.143
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2431–2452
Language:
URL:
https://aclanthology.org/2024.findings-acl.143
DOI:
10.18653/v1/2024.findings-acl.143
Bibkey:
Cite (ACL):
Amit Dhurandhar, Rahul Nair, Moninder Singh, Elizabeth Daly, and Karthikeyan Natesan Ramamurthy. 2024. Ranking Large Language Models without Ground Truth. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2431–2452, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Ranking Large Language Models without Ground Truth (Dhurandhar et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-acl.143.pdf