# AI-Assisted Decision Making with Human Learning

arXiv: https://arxiv.org/abs/2502.13062 · HTML: https://mlsanity.com/paper/2502.13062/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 58 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 30 of 32)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Explainable deep learning models in medical image analysis](https://mlsanity.com/paper/2005.13799/) (2020)
- [Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks](https://mlsanity.com/paper/1602.03616/) (2016)
- [Explainability in Deep Reinforcement Learning](https://mlsanity.com/paper/2008.06693/) (2020)
- [Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents](https://mlsanity.com/paper/2306.02704/) (2023)
- [The Assistive Multi-Armed Bandit](https://mlsanity.com/paper/1901.08654/) (2019)
- [Learning Representations by Humans, for Humans](https://mlsanity.com/paper/1905.12686/) (2019)
- [Learning When to Advise Human Decision Makers](https://mlsanity.com/paper/2209.13578/) (2022)
- [Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review](https://mlsanity.com/paper/2310.19778/) (2023)
- [Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition](https://mlsanity.com/paper/2306.14670/) (2023)
- [Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learning](https://mlsanity.com/paper/2403.05911/) (2024)
- [Explainable Reinforcement Learning via Model Transforms](https://mlsanity.com/paper/2209.12006/) (2022)
- [Towards Modeling and Influencing the Dynamics of Human Learning](https://mlsanity.com/paper/2301.00901/) (2023)
- [Accounting for AI and Users Shaping One Another: The Role of Mathematical Models](https://mlsanity.com/paper/2404.12366/) (2024)
- [A Bandit Model for Human-Machine Decision Making with Private Information and Opacity](https://mlsanity.com/paper/2007.04800/) (2020)
- [Designing Skill-Compatible AI: Methodologies and Frameworks in Chess](https://mlsanity.com/paper/2405.05066/) (2024)
- [Bias-Variance Games](https://mlsanity.com/paper/1909.03618/) (2019)
- [Diversified Recommendations for Agents with Adaptive Preferences](https://mlsanity.com/paper/2210.07773/) (2022)
- [A No Free Lunch Theorem for Human-AI Collaboration](https://mlsanity.com/paper/2411.15230/) (2024)
- [Online Recommendations for Agents with Discounted Adaptive Preferences](https://mlsanity.com/paper/2302.06014/) (2023)
- [Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces](https://mlsanity.com/paper/2306.10606/) (2023)
- [Understanding Model Selection For Learning In Strategic Environments](https://mlsanity.com/paper/2402.07588/) (2024)
- [Persuasion, Delegation, and Private Information in Algorithm-Assisted Decisions](https://mlsanity.com/paper/2402.09384/) (2024)

## Built on by (most cited first, 6 of 6)

- [Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People](https://mlsanity.com/paper/2510.20886/) (2025)
- [Human Misperception of Generative-AI Alignment: A Laboratory Experiment](https://mlsanity.com/paper/2502.14708/) (2025)
- [Learning to Decide with AI Assistance under Human-Alignment](https://mlsanity.com/paper/2605.12646/) (2026)
- [Algorithmic Feature Highlighting for Human-AI Decision-Making](https://mlsanity.com/paper/2604.22236/) (2026)
- [Human-AI Teaming Through the Lens of Calibration](https://mlsanity.com/paper/2606.10906/) (2026)
- [Human Decision-Making with AI Assistance under Correlated Features](https://mlsanity.com/paper/2606.20628/) (2026)

## Abstract (arXiv)

AI systems increasingly support human decision-making. In many cases, despite the algorithm's superior performance, the final decision remains in human hands. For example, an AI may assist doctors in determining which diagnostic tests to run, but the doctor ultimately makes the diagnosis. This paper studies such AI-assisted decision-making settings, where the human learns through repeated interactions with the algorithm. In our framework, the algorithm -- designed to maximize decision accuracy according to its own model -- determines which features the human can consider. The human then makes a prediction based on their own less accurate model. We observe that the discrepancy between the algorithm's model and the human's model creates a fundamental tradeoff: Should the algorithm prioritize recommending more informative features, encouraging the human to learn their importance, even if it results in less accurate predictions in the short term until learning occurs? Or is it preferable to forgo educating the human and instead select features that align more closely with their existing understanding, minimizing the immediate cost of learning? Our analysis reveals how this trade-off is shaped by both the algorithm's patience (the time-discount rate of its objective over multiple periods) and the human's willingness and ability to learn. We show that optimal feature selection has a surprisingly clean combinatorial characterization, reducible to a stationary sequence of feature subsets that is tractable to compute. As the algorithm becomes more "patient" or the human's learning improves, the algorithm increasingly selects more informative features, enhancing both prediction accuracy and the human's understanding.