
Given a dataset of prompts and a set of LLMs, ranking them without access to ground truth is possible by considering triplets of models.


coremsg

large-language-model-ranking-without-ground-truth-a-novel-perspective


Large Language Model Ranking without Ground Truth: A Novel Perspective



Models can be ranked without ground truth using a novel triplet approach.



Ranking Large Language Models without Ground Truth: A Novel Approach
