Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level

Larger language models have higher accu- racy on average, but are they better on ev- ery single instance (datapoint)?

Data and Resources

Cite this as

Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt (2024). Dataset: Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level. https://doi.org/10.57702/34bmylpg

DOI retrieved: December 17, 2024

Additional Info

Field Value
Created December 17, 2024
Last update December 17, 2024
Defined In https://doi.org/10.48550/arXiv.2105.06020
Author Ruiqi Zhong
More Authors
Dhruba Ghosh
Dan Klein
Jacob Steinhardt
Homepage https://github.com/ruiqi-zhong/acl2021-instance-level