# Auditing for Human Expertise

arXiv: https://arxiv.org/abs/2306.01646 · HTML: https://mlsanity.com/paper/2306.01646/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 55 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 16 of 16)

- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Strategic Classification](https://mlsanity.com/paper/1506.06980/) (2015)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [The Algorithmic Automation Problem: Prediction, Triage, and Human Effort](https://mlsanity.com/paper/1903.12220/) (2019)
- [How Do Classifiers Induce Agents To Invest Effort Strategically?](https://mlsanity.com/paper/1807.05307/) (2018)
- [Towards Unbiased and Accurate Deferral to Multiple Experts](https://mlsanity.com/paper/2102.13004/) (2021)
- [Conditional independence testing based on a nearest-neighbor estimator of conditional mutual information](https://mlsanity.com/paper/1709.01447/) (2017)
- [Bandit Learning in Decentralized Matching Markets](https://mlsanity.com/paper/2012.07348/) (2020)
- [Model-Powered Conditional Independence Test](https://mlsanity.com/paper/1709.06138/) (2017)
- [The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization](https://mlsanity.com/paper/2202.11776/) (2022)
- [Regret, stability & fairness in matching markets with bandit learners](https://mlsanity.com/paper/2102.06246/) (2021)
- [Robust inference with knockoffs](https://mlsanity.com/paper/1801.03896/) (2018)
- [On the Construction of Knockoffs in Case-Control Studies](https://mlsanity.com/paper/1812.11433/) (2018)

## Built on by (most cited first, 12 of 12)

- [Towards Human-AI Complementarity with Prediction Sets](https://mlsanity.com/paper/2405.17544/) (2024)
- [From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered](https://mlsanity.com/paper/2506.07461/) (2025)
- [Human Expertise in Algorithmic Prediction](https://mlsanity.com/paper/2402.00793/) (2024)
- [Towards Human-AI Complementarity in Matching Tasks](https://mlsanity.com/paper/2508.13285/) (2025)
- [Explaining and Improving Information Complementarities in Multi-Agent Decision-making](https://mlsanity.com/paper/2502.06152/) (2025)
- [To Ask or Not to Ask: Learning to Require Human Feedback](https://mlsanity.com/paper/2510.08314/) (2025)
- [When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-making](https://mlsanity.com/paper/2308.11721/) (2023)
- [Integrating Expert Judgment and Algorithmic Decision Making: An Indistinguishability Framework](https://mlsanity.com/paper/2410.08783/) (2024)
- [Narrowing Action Choices with AI Improves Human Sequential Decisions](https://mlsanity.com/paper/2510.16097/) (2025)
- [Understanding Fairness-Accuracy Trade-offs in Machine Learning Models: Does Promoting Fairness Undermine Performance?](https://mlsanity.com/paper/2411.17374/) (2024)
- [A Bayesian Model for Multi-stage Censoring](https://mlsanity.com/paper/2511.11684/) (2025)
- [Large Language Models in Peer-Run Community Behavioral Health Services: Understanding Peer Specialists and Service Users' Perspectives on Opportunities, Risks, and Mitigation Strategies](https://mlsanity.com/paper/2602.08187/) (2026)

## Abstract (arXiv)

High-stakes prediction tasks (e.g., patient diagnosis) are often handled by trained human experts. A common source of concern about automation in these settings is that experts may exercise intuition that is difficult to model and/or have access to information (e.g., conversations with a patient) that is simply unavailable to a would-be algorithm. This raises a natural question whether human experts add value which could not be captured by an algorithmic predictor. We develop a statistical framework under which we can pose this question as a natural hypothesis test. Indeed, as our framework highlights, detecting human expertise is more subtle than simply comparing the accuracy of expert predictions to those made by a particular learning algorithm. Instead, we propose a simple procedure which tests whether expert predictions are statistically independent from the outcomes of interest after conditioning on the available inputs (`features'). A rejection of our test thus suggests that human experts may add value to any algorithm trained on the available data, and has direct implications for whether human-AI `complementarity' is achievable in a given prediction task. We highlight the utility of our procedure using admissions data collected from the emergency department of a large academic hospital system, where we show that physicians' admit/discharge decisions for patients with acute gastrointestinal bleeding (AGIB) appear to be incorporating information that is not available to a standard algorithmic screening tool. This is despite the fact that the screening tool is arguably more accurate than physicians' discretionary decisions, highlighting that -- even absent normative concerns about accountability or interpretability -- accuracy is insufficient to justify algorithmic automation.