AI Paper Atlas

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

Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models

Guande He, Jianfei Chen, Jun Zhu

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 1 citations (OpenAlex)

This paper tried a common change: Add label smoothing

Add label smoothing to JL-P · SWAG · ECE: 1.94 -> 1.20 Improved

What 190 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
Add joint MLM training on downstream text (JL-D) (ablation)Full fine-tuning with RoBERTa-base · SNLI/MNLI, QQP/TwitterPPDB, SWAG/HellaSWAGECE: 2.21_{0.12} -> 0.67_{0.05} (SNLI); 4.06_{0.20} -> 1.26_{0.50} (MNLI); 2.44_{0.10} -> 0.57_{0.12} (QQP); 10.09_{0.49} -> Improved
Use pre-training-phase corpus instead of downstream text for the MLM objective (JL-P) (ablation)Joint learning · MNLI, TwitterPPDB, HellaSWAGECE: 1.26 -> 1.20 (MNLI); 6.49 -> 1.27 (TwitterPPDB); 7.64 -> 5.23 (HellaSWAG)Improved
Use pre-training-phase corpus for MLM instead of downstream text (ablation)Joint learning · SWAGECE: 0.91 -> 1.94Hurt
Add label smoothing to JL-P (ablation)JL-P with pre-trained-model distillation · SWAGECE: 1.94 -> 1.20Improved
Add pre-trained-model knowledge distillation to JL-D (ablation)JL-D · QQP/TwitterPPDBECE: 0.57_{0.12} -> 0.50_{0.08} (QQP); 6.49_{0.44} -> 6.06_{0.52} (TwitterPPDB)Improved
Add pre-trained-model knowledge distillation to JL-P (ablation)JL-P · SWAG/HellaSWAGECE: 2.85_{0.11} -> 1.94_{0.12} (SWAG); 7.64_{0.37} -> 5.23_{0.43} (HellaSWAG)Improved
Add pre-trained-model knowledge distillation to JL-P (ablation)JL-P · SNLIECE: 1.12_{0.17} -> 1.09_{0.15}Improved
Add pre-trained-model knowledge distillation to JL-P (ablation)JL-P · QQPECE: 0.78_{0.47} -> 0.91_{0.50}Hurt
Add contextualized-representation L2 regularization (ablation)JL-D · ID and OD settingsECEImproved
Increase the MLM loss weight (ablation)Joint learning · NLU tasksaccuracyHurt

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