AI Paper Atlas

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

Refining Language Models with Compositional Explanations

Huihan Yao, Ying Chen, Qinyuan Ye, Xisen Jin, Xiang Ren

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 17 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
add soft-matched regularization advice R_soft on top of strict noisy labels, versus labels alone (ablation)ReMoTE BERT-Large · HatEval->GHC targetTarget F1: 37.5 -> 46.1Improved
ReMoTE explanations versus fine-tune with same-time labeled sampleBERT-Large · HatEval->GHC targetTarget F1: 40.7 -> 46.1Improved
regularize both attribution and interaction rather than attribution only (ablation)ReMoTE R_soft BERT-Base · HatEval->GHC targetTarget F1: 36.8 -> 39.9Improved
add interaction regularization alone (no attribution) (ablation)ReMoTE R_soft BERT-Base · HatEval->GHC targetTarget F1: 31.8 vs 36.8 (attribution only)Hurt
use only hate-labeled rules instead of all rules (ablation)ReMoTE R_soft BERT-Base · HatEval->GHC targetTarget F1: 35.7 -> 39.9Improved
add hate-labeled rules vs nonhate-labeled rules only (ablation)ReMoTE R_soft BERT-Base · Stormfront->GHC targetTarget F1: 43.2 -> 45.7Improved
fine-tune on strict-matched noisy labels instead of random labeled sampleBERT-Base · HatEval->GHC targetTarget F1: 45.6 -> 49.0Improved
add R_soft regularization to C_strict fine-tuning (IG variant) (ablation)BERT-Base · HatEval->GHCFPRD: 80.2 -> 129.5Hurt
add R_soft regularization to C_strict fine-tuning (SOC variant) (ablation)BERT-Base · HatEval->GHC targetTarget F1: 45.1 -> 46.6Improved
increase number of explanations (ablation)ReMoTE BERT-Base · HatEval->GHC targetTarget F1Improved
ReMoTE R_soft+C_strict versus source modelRoBERTa-Base · Stormfront->GHCFPRD: 43.8 -> 77.5Hurt

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