Research map / Large language models / AI and society
Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
Yao Rong, Tobias Leemann, Thai-trang Nguyen, Lisa Fiedler, Peizhu Qian, Vaibhav Vasant Unhelkar, Tina Seidel, Gjergji Kasneci, Enkelejda Kasneci
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 |
|---|---|---|---|
| add explanations versus no explanations | user trust in AI · XAI user studies | user trust | Mixed |
| add explanations in autonomous driving | user trust · autonomous driving, simulation vs real footage | trust | Mixed |
| add SHAP explanations to white-box models versus black-box without explanations | objective understanding · simulatability tasks | simulation performance | Hurt |
| add anchors or prototype explanations | objective understanding · user study | objective understanding | No clear effect |
| add highlighted important words as explanations in text classification | user trust and satisfaction · text classification | trust and satisfaction | Hurt |
| add feature importance scores or counterfactual explanations | perceived fairness · decision explanation | perceived fairness | Improved |
| add explanations for novices versus experts | human-AI collaboration performance · human-AI decision making | human performance | Mixed |
| add model explanations for detecting incorrect predictions | failure detection · user study | incorrect prediction identification | Hurt |
Closest papers by meaning
- Position: Explainable AI Cannot Advance Without Better User Studies (ICML 2025 · similarity 0.92)
- Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics (NeurIPS 2024 · similarity 0.91)
- Position: Explain to Question not to Justify (ICML 2024 · similarity 0.90)
- Evaluating the Effectiveness of Explainable Artificial Intelligence Approaches (Student Abstract) (AAAI 2024 · similarity 0.89)
- I-CEE: Tailoring Explanations of Image Classification Models to User Expertise (AAAI 2024 · similarity 0.87)
- iLLuMinaTE: An LLM-XAI Framework Leveraging Social Science Explanation Theories Towards Actionable Student Performance Feedback (AAAI 2025 · similarity 0.87)
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.
