Research map / Label-efficient and robust learning / Recognition and long-tail
Eliminating the Impossible, Whatever Remains Must Be True: On Extracting and Applying Background Knowledge in the Context of Formal 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 |
|---|---|---|---|
| Add extracted background knowledge to formal abductive explanations | Formal explanations for DL, BT, and BNN classifiers · 62 quantized UCI/PMB datasets | AXp size | Helped |
| Add extracted background knowledge to formal contrastive explanations | Formal explanations for DL, BT, and BNN classifiers · 62 quantized UCI/PMB datasets | CXp size | Hurt |
| Add extracted background knowledge when assessing heuristic explanations | LIME · 62 datasets, DL, BT, and BNN | correctness: 6.06 -> 31.06; 38.26 -> 60.63; 8.2 -> 47.88 | Helped |
| Add extracted background knowledge when assessing heuristic explanations | SHAP · 62 datasets, DL, BT, and BNN | correctness: 49.47 -> 91.72; 72.89 -> 93.75; 58.89 -> 95.0 | Helped |
| Add extracted background knowledge when assessing heuristic explanations | Anchor · 62 datasets, DL, BT, and BNN | correctness: 24.03 -> 73.85; 13.85 -> 73.0; 6.57 -> 70.1 | Helped |
| Extract background rules with the proposed MaxSAT method | Background knowledge rules · 62 quantized UCI/PMB datasets, test folds | rule accuracy: 99.22; 99.35; 99.29; 99.16; 99.06; 99.08 | Helped |
Closest papers by meaning
- Delivering Inflated Explanations (AAAI 2024 · similarity 0.88)
- Reliable Post hoc Explanations: Modeling Uncertainty in Explainability (NeurIPS 2021 · similarity 0.87)
- xWhy: Causal Learning from Explanations (NeurIPS 2026 · similarity 0.87)
- Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution (AAAI 2025 · similarity 0.85)
- How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations (ICLR 2025 · similarity 0.85)
- Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint) (AAAI 2024 · similarity 0.85)
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.