# Should I stay or should I show? Learning to selectively disclose information

arXiv: https://arxiv.org/abs/2609.39818 · HTML: https://mlsanity.com/paper/2609.39818/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 85 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 30 of 45)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [Quasi-Oracle Estimation of Heterogeneous Treatment Effects](https://mlsanity.com/paper/1712.04912/) (2017)
- [Adapting Neural Networks for the Estimation of Treatment Effects](https://mlsanity.com/paper/1906.02120/) (2019)
- [Least Ambiguous Set-Valued Classifiers with Bounded Error Levels](https://mlsanity.com/paper/1609.00451/) (2016)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [Learning to Complement Humans](https://mlsanity.com/paper/2005.00582/) (2020)
- [EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE](https://mlsanity.com/paper/1809.11142/) (2018)
- [Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations](https://mlsanity.com/paper/2302.02187/) (2023)
- [Differentiable Learning Under Triage](https://mlsanity.com/paper/2103.08902/) (2021)
- [Who Should Predict? Exact Algorithms For Learning to Defer to Humans](https://mlsanity.com/paper/2301.06197/) (2023)
- [Calibrated Learning to Defer with One-vs-All Classifiers](https://mlsanity.com/paper/2202.03673/) (2022)
- [Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making](https://mlsanity.com/paper/2301.05809/) (2023)
- [Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles](https://mlsanity.com/paper/2210.16955/) (2022)
- [Role of Human-AI Interaction in Selective Prediction](https://mlsanity.com/paper/2112.06751/) (2021)
- [Conformal Prediction Sets Improve Human Decision Making](https://mlsanity.com/paper/2401.13744/) (2024)
- [Complementarity in Human-AI Collaboration: Concept, Sources, and Evidence](https://mlsanity.com/paper/2404.00029/) (2024)
- [Human-AI Collaboration: The Effect of AI Delegation on Human Task Performance and Task Satisfaction](https://mlsanity.com/paper/2303.09224/) (2023)
- [Designing Decision Support Systems Using Counterfactual Prediction Sets](https://mlsanity.com/paper/2306.03928/) (2023)
- [In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer](https://mlsanity.com/paper/2311.01106/) (2023)
- [Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters](https://mlsanity.com/paper/2104.04103/) (2021)
- [Towards Human-AI Complementarity with Prediction Sets](https://mlsanity.com/paper/2405.17544/) (2024)
- [Classification with Costly Features as a Sequential Decision-Making Problem](https://mlsanity.com/paper/1909.02564/) (2019)
- [Learning When to Advise Human Decision Makers](https://mlsanity.com/paper/2209.13578/) (2022)
- [A Two-Stage Learning-to-Defer Approach for Multi-Task Learning](https://mlsanity.com/paper/2410.15729/) (2024)
- [A Survey on Active Feature Acquisition Strategies](https://mlsanity.com/paper/2502.11067/) (2025)
- [Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models](https://mlsanity.com/paper/2406.07212/) (2024)
- [Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees](https://mlsanity.com/paper/2502.01027/) (2025)

## Abstract (arXiv)

In many high-stakes settings, human decision-makers can acquire support information before making a decision. However, acquiring information is costly, and disclosure may fail to improve human decisions or may even impair them. We tackle this problem by studying selective disclosure, i.e., the problem of learning when to reveal support information to a human decision-maker under a budget constraint. We first show that the optimal policy is a threshold rule on the Value of Information (VoI), i.e., the expected reduction in human decision risk induced by disclosure. Since VoI is unknown in practice, we estimate the regime-specific human risks and bound the possible degradation of the resulting plug-in policy relative to lack of disclosure, as well as its regret relative to the optimal policy. Experiments on benchmark datasets show that selective disclosure outperforms both no disclosure and full disclosure, regardless of whether the support information is beneficial or harmful. Two user studies show that human-AI team performance can improve when disclosure is led by our learned policy and not human-selected, although this advantage varies across tasks. A counterfactual benchmark, which replaces participants' predictions with a machine-learning prediction when disclosure occurs, suggests that these differences might depend on lower adherence to advice when the information is automatically provided rather than self-requested.