mlsanityData to 14 Oct 2026

Learning When to Advise Human Decision Makers

arXiv 2209.13578 ↗First posted 27 Sep 2022cs.AI cs.HC cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence (AI) systems are increasingly used for providing advice to facilitate human decision making in a wide range of domains, such as healthcare, criminal justice, and finance. Motivated by limitations of the current practice where algorithmic advice is provided to human users as a constant element in the decision-making pipeline, in this paper we raise the question of when should algorithms provide advice? We propose a novel design of AI systems in which the algorithm interacts with the human user in a two-sided manner and aims to provide advice only when it is likely to be beneficial for the user in making their decision. The results of a large-scale experiment show that our advising approach manages to provide advice at times of need and to significantly improve human decision making compared to fixed, non-interactive, advising approaches. This approach has additional advantages in facilitating human learning, preserving complementary strengths of human decision makers, and leading to more positive responsiveness to the advice.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 29 of its 103 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

29 of 103 references.

References · 29

  1. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  2. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  3. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  4. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  5. 2020Consistent Estimators for Learning to Defer to an Expertcited by 271
  6. 2015Strategic Classificationcited by 257
  7. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  8. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 233
  9. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 206
  10. 2019Predictive Multiplicity in Classificationcited by 166
  11. 2018On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detectioncited by 159
  12. 2017Strategic Classification from Revealed Preferencescited by 128
17 more
  1. 2020Learning to Complement Humanscited by 124
  2. 2020Explainable deep learning models in medical image analysiscited by 111
  3. 2021Machine Learning with a Reject Option: A surveycited by 109
  4. 2020Explainability in Deep Reinforcement Learningcited by 97
  5. 2020"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humanscited by 86
  6. 2021Strategic Classification in the Darkcited by 66
  7. 2021Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Makingcited by 58
  8. 2021Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowdscited by 58
  9. 2021The Flaws of Policies Requiring Human Oversight of Government Algorithmscited by 44
  10. 2014Optimum Statistical Estimation with Strategic Data Sourcescited by 28
  11. 2021Auctions Between Regret-Minimizing Agentscited by 22
  12. 2021How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agentscited by 17
  13. 2020Bid Prediction in Repeated Auctions with Learningcited by 14
  14. 2022Explainable Reinforcement Learning via Model Transformscited by 11
  15. 2016Behavior-Based Machine-Learning: A Hybrid Approach for Predicting Human Decision Makingcited by 5
  16. 2019Neural Networks for Predicting Human Interactions in Repeated Gamescited by 4
  17. 2022Finding Safe Zones of policies Markov Decision Processescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 6; 2026: 3.

18 papers.

Sort:

By area:

  1. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 106
  2. 2023Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressurecited by 17
  3. 2023Learning Personalized Decision Support Policiescited by 14
  4. 2024Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skillscited by 14
  5. 2024Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learningcited by 13
  6. 2025AI-Assisted Decision Making with Human Learningcited by 6
  7. 2025Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedbackcited by 6
  8. 2024Designing Algorithmic Recommendations to Achieve Human-AI Complementaritycited by 4
  9. 2025Human Misperception of Generative-AI Alignment: A Laboratory Experimentcited by 4
  10. 2023Decongestion by Representation: Learning to Improve Economic Welfare in Marketplacescited by 3
  11. 2023User Friendly and Adaptable Discriminative AI: Using the Lessons from the Success of LLMs and Image Generation Modelscited by 1
  12. 2025Bayesian Inference for Correlated Human Experts and Classifierscited by 1
6 more
  1. 2025Collaborating with GenAI: Incentives and Replacementscited by 1
  2. 2026Learning to Decide with AI Assistance under Human-Alignmentcited by 1
  3. 2024The Value of AI Advice: Personalized and Value-Maximizing AI Advisors Are Necessary to Reliably Benefit Experts and Organizationscited by 0
  4. 2025Dynamic Trust Calibration Using Contextual Banditscited by 0
  5. 2026Human Decision-Making with AI Assistance under Correlated Featurescited by 0
  6. 2026Should I stay or should I show? Learning to selectively disclose informationcited by 0