@misc{elangovan2024beyond, title={Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge}, author={Aparna Elangovan and Jongwoo Ko and Lei Xu and Mahsa Elyasi and Ling Liu and Sravan Bodapati and Dan Roth}, year={2024}, eprint={2410.03775}, archivePrefix={arXiv}, primaryClass={cs.HC}, url={https://arxiv.org/abs/2410.03775} }