Research map / Learning theory and algorithms / Prediction and decision losses
Anchors: High-Precision Model-Agnostic Explanations
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 |
|---|---|---|---|
| use anchor rule explanations instead of linear LIME explanations | simulated users · adult/rcdv/lending | precision: 65.7 -> 93.4 | Helped |
| use anchors instead of threshold-tuned LIME | simulated users · adult/rcdv/lending | coverage | Mixed |
| use one anchor explanation instead of one LIME explanation | human users · User study vqa1 | human precision: 57.5 -> 93.0 | Helped |
| use anchors instead of LIME | human users · User study adult | time per prediction: 28.5±10 -> 13.0±4 | Helped |
| use two anchors instead of two LIME explanations | human users · User study adult | human precision: 89.9 -> 87.4 | Hurt |
| pick explanations by submodular pick instead of random (ablation) | Anchor · rcdv simulated users | coverage | Helped |
Closest papers by meaning
- Learning Robust Rationales for Model Explainability: A Guidance-Based Approach (AAAI 2024 · similarity 0.84)
- Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals (AAAI 2024 · similarity 0.84)
- Compact Proofs of Model Performance via Mechanistic Interpretability (NeurIPS 2024 · similarity 0.84)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.83)
- Accelerating the Global Aggregation of Local Explanations (AAAI 2024 · similarity 0.83)
- A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability (ICML 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.