Research map / Large language models / Language, safety and interpretability
Use-Case-Grounded Simulations for Explanation Evaluation
Valerie Chen, Nari Johnson, Nicholay Topin, Gregory Plumb, Ameet Talwalkar
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Provide LIME explanations instead of no explanation | SimEvals agent · Forward simulation | agent test accuracy: 88.7% -> 100% | Improved |
| Provide LIME explanations instead of Anchors | SimEvals agent · Forward simulation | agent test accuracy: 93.7% -> 100% | Improved |
| Provide LIME explanations instead of SHAP, GAM, or no explanation | SimEvals agent · Counterfactual reasoning | agent test accuracy: 64.9% -> 99.7%; 63.5% -> 99.7%; 60.3% -> 99.7% | Improved |
| Provide LIME explanations instead of other explanation settings | Human participants · Counterfactual reasoning | human test accuracy: 41.4% ± 6.14% to 69.4% ± 12.4%; 45.7% ± 7.19% to 69.4% ± 12.4%; 48.6% ± 5.61% to 69.4% ± 12.4% | Improved |
| Provide SHAP explanations instead of LIME | SimEvals agent · Missing values bug | agent test accuracy: 75.9% -> 100% | Improved |
| Provide GAM explanations instead of LIME | SimEvals agent · Missing values bug | agent test accuracy: 75.9% -> 100% | Improved |
| Provide SHAP or GAM explanations instead of LIME or model predictions | Human participants · Missing values bug | human test accuracy: 48.0% -> 67.4%; 40.7% -> 67.4%; 48.0% -> 64.4%; 40.7% -> 64.4% | Improved |
| Increase the number of data-points per observation from 1 to 1000 (ablation) | SimEvals agent with SHAP · Missing values bug | agent test accuracy: 63.2% -> 100% | Improved |
| Increase the number of data-points per observation from 1 to 1000 (ablation) | SimEvals agent with GAM · Missing values bug | agent test accuracy: 64.8% -> 100% | Improved |
| Increase the number of data-points per observation from 1 to 1000 (ablation) | SimEvals agent with LIME · Missing values bug | agent test accuracy: 55.2% -> 75.9% | Improved |
| Increase the number of data-points per observation from 1 to 1000 (ablation) | SimEvals agent with Model Prediction · Missing values bug | agent test accuracy: 57.5% -> 67.3% | Improved |
Closest papers by meaning
- Position: Explainable AI Cannot Advance Without Better User Studies (ICML 2025 · similarity 0.86)
- On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods (AAAI 2024 · similarity 0.83)
- iLLuMinaTE: An LLM-XAI Framework Leveraging Social Science Explanation Theories Towards Actionable Student Performance Feedback (AAAI 2025 · similarity 0.83)
- Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments (AAAI 2025 · similarity 0.83)
- Automated Assessment of Fidelity and Interpretability: An Evaluation Framework for Large Language Models’ Explanations (Student Abstract) (AAAI 2024 · similarity 0.82)
- Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution (AAAI 2025 · similarity 0.82)
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.
