%0 Journal Article %1 journals/corr/abs-2401-16788 %A Chern, Steffi %A Chern, Ethan %A Neubig, Graham %A Liu, Pengfei %D 2024 %J CoRR %K dblp %T Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate. %U http://dblp.uni-trier.de/db/journals/corr/corr2401.html#abs-2401-16788 %V abs/2401.16788

@article{journals/corr/abs-2401-16788, added-at = {2024-02-06T00:00:00.000+0100}, author = {Chern, Steffi and Chern, Ethan and Neubig, Graham and Liu, Pengfei}, biburl = {https://www.bibsonomy.org/bibtex/251ce51a23b20279b823cf4fe617b3099/dblp}, ee = {https://doi.org/10.48550/arXiv.2401.16788}, interhash = {8f74ff9dd9b920928cb358896715f8b6}, intrahash = {51ce51a23b20279b823cf4fe617b3099}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:07:13.000+0200}, title = {Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2401.html#abs-2401-16788}, volume = {abs/2401.16788}, year = 2024 }