When Combating Hype, Proceed with Caution

By Samuel R. Bowman. 2021

7 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Matt Gardner
2. Pradeep Dasigi
3. Yuxiang Wu
4. Pontus Stenetorp
5. Daniel Khashabi
6. Jonathan Berant
7. Tushar Khot
8. Eric Wallace

Citations in the corpus

• Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets (2022, methodology): “…generalisation performance than BERT-base, which agrees with Bhargava et al. 8 Details of the subcategories are described in Appendix C. (2021); Bowman (2021); 2) training on our debi-ased datasets can still improve the performance of these models, yielding an average 2.30%, 1.23%, 1.13% gain…”