Research map / Large language models / AI and society
Does Explainable Artificial Intelligence Improve Human Decision-Making?
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 |
|---|---|---|---|
| Provide an AI prediction rather than no AI information | Human decision-making · Census income | decision accuracy | Helped |
| Provide an AI prediction with an anchor LIME explanation rather than no AI information | Human decision-making · Census income | decision accuracy | Helped |
| Add an anchor LIME explanation to the AI prediction | Human decision-making · Census income | decision accuracy: p = 0.28 | No clear effect |
| Provide an AI prediction or an AI prediction with explanation rather than no AI information | Human decision-making · COMPAS | decision accuracy: ps > 0.75 | No clear effect |
| Add an anchor LIME explanation to the AI prediction | Human decision-making · Census income and COMPAS | decision accuracy: ps > 0.60 | No clear effect |
| Increase the accuracy of the AI prediction shown to participants | Human decision-making · Census income and COMPAS | decision accuracy: β = 0.70, p < 0.001, R^2 = 0.28 | Helped |
| Add an anchor LIME explanation to the AI prediction | Human decision-making · Census income and COMPAS | ability to outperform AI accuracy | No clear effect |
| Add an anchor LIME explanation to the AI prediction | Human decision-making · Census income and COMPAS | following AI recommendations: p = 0.62 | No clear effect |
| Provide AI information rather than no AI information | Human decision-making · Census income and COMPAS | confidence: p < 0.03 | Helped |
| Add an anchor LIME explanation to the AI prediction | Human decision-making · Census income and COMPAS | confidence: ps > 0.25 | No clear effect |
| Show AI predictions that are correct rather than incorrect | Human decision-making · Census income and COMPAS | following AI recommendations: F(1,196) = 36.15, p < 0.001, η_p^2 = 0.16 | Helped |
| Add an anchor LIME explanation to the AI prediction | Human decision-making · Census income and COMPAS | reaction time: F(2,294) = 2.13, p = 0.12, η^2 = 0.01 | No clear effect |
Closest papers by meaning
- Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary (NeurIPS 2024 · similarity 0.91)
- Position: Explainable AI Cannot Advance Without Better User Studies (ICML 2025 · similarity 0.90)
- Decoding AI’s Nudge: A Unified Framework to Predict Human Behavior in AI-Assisted Decision Making (AAAI 2024 · similarity 0.87)
- Position: Explain to Question not to Justify (ICML 2024 · similarity 0.87)
- Evaluating the Effectiveness of Explainable Artificial Intelligence Approaches (Student Abstract) (AAAI 2024 · similarity 0.87)
- Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics (NeurIPS 2024 · similarity 0.86)
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.