AI Paper Atlas

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

Missingness Bias Calibration in Feature Attribution Explanations

Shailesh Sridhar, Anton Xue, Eric Wong

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 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
add MCal linear logit calibratorfrozen base classifiers · 8 medical benchmarks (vision, language, tabular)KL missingness bias: e.g. CheXpert 1.70e-1 -> 8.82e-3; MedQA 1.61e-1 -> 9.44e-4Improved
use MCal instead of retraining the model on ablated inputsViT-B16 · Brain MRIKL missingness bias: 6.70e-4 (Retrain) vs 7.43e-3 (MCal)Hurt
use MCal instead of retrainingLlama-3.1-8B-Instruct · MedQAKL missingness bias: 1.70e-1 -> 9.44e-4Improved
use MCal instead of retrainingXGBoost · PhysioNet, Breast Cancer, CTGKL missingness bias: Breast Cancer 5.68e-3 -> 1.92e-5Mixed
use MCal instead of temperature scalingLlama-3.1-8B-Instruct · MedMCQAKL missingness bias: 7.81e-1 -> 9.01e-3Improved
use architecture-native support for missing features (Arch)XGBoost · Breast Cancer and CTGKL missingness bias: 1.02e-1 -> 2.13e-1; 1.06e-1 -> 2.85e-1Hurt
use replacement-based imputation (Replace)base classifiers · 8 medical benchmarksKL missingness bias: CheXpert 1.70e-1 -> 9.70e-2; BreakHis 1.87e-1 -> 4.20e-1Mixed
condition calibrators on ablation rate (ensemble) vs a single unconditioned calibrator (ablation)MCal · MRI, MedQA, PhysioNetmissingness biasImproved
add MCal (conditioned or unconditioned)base classifiers · accuracy under ablationaccuracyImproved

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