Research map / Learning theory and algorithms / Prediction and decision losses
Human-Aligned Calibration for AI-Assisted 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 |
|---|---|---|---|
| Use human confidence after AI advice instead of before advice | Human decision policy · Art | AUC: 72.7\% -> 82.0\% | Helped |
| Use human confidence after AI advice instead of before advice | Human decision policy · Sarcasm | AUC: 82.5\% -> 86.5\% | Helped |
| Use human confidence after AI advice instead of before advice | Human decision policy · Cities | AUC: 79.0\% -> 84.7\% | Helped |
| Use human confidence after AI advice instead of before advice | Human decision policy · Census | AUC: 77.3\% -> 79.9\% | Helped |
| Use human confidence after AI advice instead of classifier confidence | AI-assisted decision policy · Art | AUC: 86.7\% -> 82.0\% | Hurt |
| Use human confidence after AI advice instead of classifier confidence | AI-assisted decision policy · Sarcasm | AUC: 89.9\% -> 86.5\% | Hurt |
| Use human confidence after AI advice instead of classifier confidence | AI-assisted decision policy · Cities | AUC: 84.4\% -> 84.7\% | Helped |
| Use human confidence after AI advice instead of classifier confidence | AI-assisted decision policy · Census | AUC: 80.0\% -> 79.9\% | Hurt |
| Provide classifier confidence that is human-aligned rather than not human-aligned | AI-assisted decision making · Four decision tasks | AUC | Mixed |
Closest papers by meaning
- Learning to Decide with AI Assistance under Human-Alignment (NeurIPS 2026 · similarity 0.93)
- Measuring Error Alignment for Decision-Making Systems (AAAI 2025 · similarity 0.87)
- A Unifying Normative Framework of Decision Confidence (NeurIPS 2024 · similarity 0.87)
- Testable and Actionable Calibration for Full Swap Regret (NeurIPS 2026 · similarity 0.86)
- U-trustworthy Models. Reliability, Competence, and Confidence in Decision-Making (AAAI 2024 · similarity 0.86)
- Conformal Prediction Sets Improve Human Decision Making (ICML 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.