Pith. sign in

REVIEW 1 cited by

MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.11402 v1 pith:MZX4OZJS submitted 2021-02-22 cs.CL cs.LG

Wancong Zhang , Ieshan Vaidya This is my paper · ORCID
classification cs.CLcs.LG
keywords mixupmodelinputarchitecturecalibrationdatatrainingtransformer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding (NLU) domain has been limited, due to the difficulty of interpolating text directly in the input space. In this study, we propose MixUp methods at the Input, Manifold, and sentence embedding levels for the transformer architecture, and apply them to finetune the BERT model for a diverse set of NLU tasks. We find that MixUp can improve model performance, as well as reduce test loss and model calibration error by up to 50%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Mitigating Shortcut Learning with InterpoLated Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    InterpoLL improves minority generalization by interpolating representations of majority examples with intra-class minority examples during training.

Pith tools