Research map / Label-efficient and robust learning / Recognition and long-tail
Examples are not enough, learn to criticize! Criticism for Interpretability
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| add criticisms to prototypes (ablation) | MMD-critic · human study | human accuracy: 75% -> 87.5% | Helped |
| add criticisms to prototypes (ablation) | MMD-critic · human study | time per question (mins): 1.04 -> 1.37 | Hurt |
| prototypes plus criticisms vs uniform sampling | MMD-critic · human study | human accuracy: 55% -> 87.5% | Helped |
| prototypes plus criticisms vs raw images | MMD-critic · human study | human accuracy: 56% -> 87.5% | Helped |
| prototypes only vs raw images | MMD-critic · human study | time per question (mins): 1.86 -> 1.04 | Helped |
| prototypes only vs uniform sampling | MMD-critic · human study | human accuracy: 55% -> 75% | Helped |
| use global kernel instead of local kernel | MMD-critic · USPS | test error vs number of prototypes | Helped |
| MMD-critic vs baselines (PS, K-medoids) for few prototypes | MMD-critic · USPS | test error vs number of prototypes | Helped |
Closest papers by meaning
- Automated Assessment of Fidelity and Interpretability: An Evaluation Framework for Large Language Models’ Explanations (Student Abstract) (AAAI 2024 · similarity 0.86)
- Towards Automating Model Explanations with Certified Robustness Guarantees (AAAI 2022 · similarity 0.85)
- Human-in-the-Loop Interpretability Prior (NeurIPS 2018 · similarity 0.84)
- Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling (AAAI 2023 · similarity 0.84)
- Enhancing Performance of Explainable AI Models with Constrained Concept Refinement (ICML 2025 · similarity 0.83)
- Maximizing Signal in Human-Model Preference Alignment (AAAI 2025 · similarity 0.83)
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.