# Human Decision-Making with AI Assistance under Correlated Features

arXiv: https://arxiv.org/abs/2606.20628 · HTML: https://mlsanity.com/paper/2606.20628/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 12 of 12)

- [Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations](https://mlsanity.com/paper/2301.07255/) (2023)
- [On Explore-Then-Commit Strategies](https://mlsanity.com/paper/1605.08988/) (2016)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [Multi-Armed Bandits with Correlated Arms](https://mlsanity.com/paper/1911.03959/) (2019)
- [A Decision Theoretic Framework for Measuring AI Reliance](https://mlsanity.com/paper/2401.15356/) (2024)
- [Learning When to Advise Human Decision Makers](https://mlsanity.com/paper/2209.13578/) (2022)
- [Human Expertise in Algorithmic Prediction](https://mlsanity.com/paper/2402.00793/) (2024)
- [A No Free Lunch Theorem for Human-AI Collaboration](https://mlsanity.com/paper/2411.15230/) (2024)
- [AI-Assisted Decision Making with Human Learning](https://mlsanity.com/paper/2502.13062/) (2025)
- [Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff](https://mlsanity.com/paper/2506.03102/) (2025)
- [Humans learn too: Better Human-AI Interaction using Optimized Human Inputs](https://mlsanity.com/paper/2009.09266/) (2020)
- [Clinical Recommender System: Predicting Medical Specialty Diagnostic Choices with Neural Network Ensembles](https://mlsanity.com/paper/2007.12161/) (2020)

## Abstract (arXiv)

Humans increasingly make decisions with AI assistance; for example, doctors may follow AI-recommended diagnostic tests and base their diagnoses on the results. A natural question is which tests should AI recommend to balance short-term decision quality and long-term human learning when different features (e.g., test results) are correlated. While prior work establishes that stationary policies that recommend the same tests repeatedly are optimal when features are independent, we prove that feature correlations lead such policies to perform arbitrarily poorly. Instead, we prove that any optimal policy must follow an explore-then-commit structure; initially, the AI should offer diverse tests so humans can learn accurate feature coefficients, then the AI should commit to a single set of tests, with exploration length that depends on the degree of feature correlation. We prove that computing the optimal policy is NP-hard and derive a dynamic programming-based algorithm that finds the optimal policy for finite horizons. We additionally develop an approximation that plans for shorter horizons and appends a stationary suffix, achieving near-optimal performance. Our empirical results complement our theory by showing that stronger feature correlation leads to longer exploration phases.