# Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making

arXiv: https://arxiv.org/abs/2302.06503 · HTML: https://mlsanity.com/paper/2302.06503/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 112 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 30 of 51)

- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems](https://mlsanity.com/paper/2001.08298/) (2020)
- [Learning to Complement Humans](https://mlsanity.com/paper/2005.00582/) (2020)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Runaway Feedback Loops in Predictive Policing](https://mlsanity.com/paper/1706.09847/) (2017)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- ["Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans](https://mlsanity.com/paper/2001.05871/) (2020)
- [Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies](https://mlsanity.com/paper/2112.11471/) (2021)
- [Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects](https://mlsanity.com/paper/2001.07426/) (2020)
- [Classification with Asymmetric Label Noise: Consistency and Maximal Denoising](https://mlsanity.com/paper/1303.1208/) (2013)
- [Fair Classification with Group-Dependent Label Noise](https://mlsanity.com/paper/2011.00379/) (2020)
- [Designing Toxic Content Classification for a Diversity of Perspectives](https://mlsanity.com/paper/2106.04511/) (2021)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [Counterfactual Risk Assessments, Evaluation, and Fairness](https://mlsanity.com/paper/1909.00066/) (2019)
- [Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making](https://mlsanity.com/paper/2101.05303/) (2021)
- [Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning](https://mlsanity.com/paper/2202.05402/) (2022)
- [Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation](https://mlsanity.com/paper/2112.04554/) (2021)
- [Residual Unfairness in Fair Machine Learning from Prejudiced Data](https://mlsanity.com/paper/1806.02887/) (2018)
- [Sample Efficient Learning of Predictors that Complement Humans](https://mlsanity.com/paper/2207.09584/) (2022)
- [Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness](https://mlsanity.com/paper/2202.08821/) (2022)
- [Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support](https://mlsanity.com/paper/2204.02310/) (2022)
- [Fairness Evaluation in Presence of Biased Noisy Labels](https://mlsanity.com/paper/2003.13808/) (2020)

## Built on by (most cited first, 25 of 25)

- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Explore, Establish, Exploit: Red Teaming Language Models from Scratch](https://mlsanity.com/paper/2306.09442/) (2023)
- [SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback](https://mlsanity.com/paper/2410.18141/) (2024)
- [Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia](https://mlsanity.com/paper/2402.14147/) (2024)
- [Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learning](https://mlsanity.com/paper/2403.05911/) (2024)
- [AI Mismatches: Identifying Potential Algorithmic Harms Before AI Development](https://mlsanity.com/paper/2502.18682/) (2025)
- [The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning](https://mlsanity.com/paper/2410.09600/) (2024)
- [Training Towards Critical Use: Learning to Situate AI Predictions Relative to Human Knowledge](https://mlsanity.com/paper/2308.15700/) (2023)
- [The Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action](https://mlsanity.com/paper/2404.12143/) (2024)
- [Tempo: Helping Data Scientists and Domain Experts Collaboratively Specify Predictive Modeling Tasks](https://mlsanity.com/paper/2502.10526/) (2025)
- [Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness](https://mlsanity.com/paper/2506.04193/) (2025)
- [From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions](https://mlsanity.com/paper/2406.18865/) (2024)
- [Evaluating and Correcting Performative Effects of Decision Support Systems via Causal Domain Shift](https://mlsanity.com/paper/2403.00886/) (2024)
- [Correcting for Selection Bias and Missing Response in Regression using Privileged Information](https://mlsanity.com/paper/2303.16800/) (2023)
- [Predictive Performance Comparison of Decision Policies Under Confounding](https://mlsanity.com/paper/2404.00848/) (2024)
- [Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond](https://mlsanity.com/paper/2507.08866/) (2025)
- [HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning](https://mlsanity.com/paper/2510.15144/) (2025)
- [The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation](https://mlsanity.com/paper/2602.11318/) (2026)
- [Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models](https://mlsanity.com/paper/2410.19812/) (2024)
- [Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks](https://mlsanity.com/paper/2507.02819/) (2025)
- [AI as Teammate or Tool? A Review of Human-AI Interaction in Decision Support](https://mlsanity.com/paper/2602.15865/) (2026)
- [To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems](https://mlsanity.com/paper/2604.28053/) (2026)
- [Who Leads? Comparing Human-Centric and Model-Centric Strategies for Defining ML Target Variables](https://mlsanity.com/paper/2510.25974/) (2025)
- [A Bayesian Model for Multi-stage Censoring](https://mlsanity.com/paper/2511.11684/) (2025)
- [Falsifying Discriminant Validity of Predictive Algorithms](https://mlsanity.com/paper/2601.17146/) (2026)

## Abstract (arXiv)

A growing literature on human-AI decision-making investigates strategies for combining human judgment with statistical models to improve decision-making. Research in this area often evaluates proposed improvements to models, interfaces, or workflows by demonstrating improved predictive performance on "ground truth" labels. However, this practice overlooks a key difference between human judgments and model predictions. Whereas humans reason about broader phenomena of interest in a decision -- including latent constructs that are not directly observable, such as disease status, the "toxicity" of online comments, or future "job performance" -- predictive models target proxy labels that are readily available in existing datasets. Predictive models' reliance on simplistic proxies makes them vulnerable to various sources of statistical bias. In this paper, we identify five sources of target variable bias that can impact the validity of proxy labels in human-AI decision-making tasks. We develop a causal framework to disentangle the relationship between each bias and clarify which are of concern in specific human-AI decision-making tasks. We demonstrate how our framework can be used to articulate implicit assumptions made in prior modeling work, and we recommend evaluation strategies for verifying whether these assumptions hold in practice. We then leverage our framework to re-examine the designs of prior human subjects experiments that investigate human-AI decision-making, finding that only a small fraction of studies examine factors related to target variable bias. We conclude by discussing opportunities to better address target variable bias in future research.