AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learn from A Rationalist: Distilling Intermediate Interpretable Rationales

Jiayi Dai, Randy Goebel

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
distill teacher rationales and predictions into student (REKD)ViT Small RE · CIFAR-10accuracy: .889 -> .968Improved
distill teacher rationales and predictions into student (REKD)ViT Tiny RE · CIFAR-10accuracy: .797 -> .936Improved
distill teacher into student (REKD)ViT Small RE · CIFAR-100 (20 coarse classes)accuracy: .779 -> .845Improved
distill teacher into student (REKD)ViT Tiny RE · CIFAR-100 (20 coarse classes)accuracy: .645 -> .777Improved
distill teacher into student (REKD)BERT Small RE · IMDBaccuracy: .881 -> .906Improved
distill teacher into student (REKD)BERT Mini RE · IMDBaccuracy: .863 -> .892Improved
use a smaller backbone for RE (less capable base model) (ablation)RE with ViT · CIFAR-10accuracy: CLS-to-RE drop: .020 (Base), .092 (Small)Hurt
lower target rationale ratio ptarget (5% to 75% varied) (ablation)ViT RE · CIFAR-10accuracy: accuracy rises with rationale lengthMixed
REKD students versus black-box CLS studentsBERT Small and Mini · IMDBaccuracy: .906 vs .889 (Small); .892 vs .877 (Mini)Improved
REKD student versus its Base RE teacher averageViT Small · CIFAR-10accuracy: .968 vs .964No clear effect
REKD student versus its Base RE teacher averageViT Small · CIFAR-100 (20 coarse classes)accuracy: .845 vs .830Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy