On Evaluation of Document Classification with RVL-CDIP

Stefan Larson, Gordon Lim, Kevin Leach


Abstract
The RVL-CDIP benchmark is widely used for measuring performance on the task of document classification. Despite its widespread use, we reveal several undesirable characteristics of the RVL-CDIP benchmark. These include (1) substantial amounts of label noise, which we estimate to be 8.1% (ranging between 1.6% to 16.9% per document category); (2) presence of many ambiguous or multi-label documents; (3) a large overlap between test and train splits, which can inflate model performance metrics; and (4) presence of sensitive personally-identifiable information like US Social Security numbers (SSNs). We argue that there is a risk in using RVL-CDIP for benchmarking document classifiers, as its limited scope, presence of errors (state-of-the-art models now achieve accuracy error rates that are within our estimated label error rate), and lack of diversity make it less than ideal for benchmarking. We further advocate for the creation of a new document classification benchmark, and provide recommendations for what characteristics such a resource should include.
Anthology ID:
2023.eacl-main.195
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2665–2678
Language:
URL:
https://aclanthology.org/2023.eacl-main.195
DOI:
10.18653/v1/2023.eacl-main.195
Bibkey:
Cite (ACL):
Stefan Larson, Gordon Lim, and Kevin Leach. 2023. On Evaluation of Document Classification with RVL-CDIP. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2665–2678, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
On Evaluation of Document Classification with RVL-CDIP (Larson et al., EACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2023.eacl-main.195.pdf
Dataset:
 2023.eacl-main.195.dataset.zip
Video:
 https://preview.aclanthology.org/landing_page/2023.eacl-main.195.mp4