mlsanityData to 7 Oct 2026

Complementarity in Human-AI Collaboration: Concept, Sources, and Evidence

arXiv 2404.00029 ↗First posted 21 Mar 2024cs.HC cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence (AI) has the potential to significantly enhance human performance across various domains. Ideally, collaboration between humans and AI should result in complementary team performance (CTP) -- a level of performance that neither of them can attain individually. So far, however, CTP has rarely been observed, suggesting an insufficient understanding of the principle and the application of complementarity. Therefore, we develop a general concept of complementarity and formalize its theoretical potential as well as the actual realized effect in decision-making situations. Moreover, we identify information and capability asymmetry as the two key sources of complementarity. Finally, we illustrate the impact of each source on complementarity potential and effect in two empirical studies. Our work provides researchers with a comprehensive theoretical foundation of human-AI complementarity in decision-making and demonstrates that leveraging these sources constitutes a viable pathway towards designing effective human-AI collaboration, i.e., the realization of CTP.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 35 of its 143 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

35 of 143 references.

References · 35

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  6. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  7. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  8. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  9. 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
  10. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 228
  11. 2021Partial success in closing the gap between human and machine visioncited by 185
  12. 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 138
23 more
  1. 2020Learning to Complement Humanscited by 123
  2. 2020Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systemscited by 100
  3. 2023The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Developmentcited by 95
  4. 2020"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humanscited by 86
  5. 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Makingcited by 67
  6. 2021Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Makingcited by 58
  7. 2021Hybrid Intelligencecited by 55
  8. 2020Does Explainable Artificial Intelligence Improve Human Decision-Making?cited by 49
  9. 2024Thousands of AI Authors on the Future of AIcited by 48
  10. 2022Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairnesscited by 45
  11. 2017When Will AI Exceed Human Performance? Evidence from AI Expertscited by 41
  12. 2022Forming Effective Human-AI Teams: Building Machine Learning Models that Complement the Capabilities of Multiple Expertscited by 40
  13. 2023Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systemscited by 40
  14. 2022Advancing Human-AI Complementarity: The Impact of User Expertise and Algorithmic Tuning on Joint Decision Makingcited by 33
  15. 2022Should I Follow AI-based Advice? Measuring Appropriate Reliance in Human-AI Decision-Makingcited by 28
  16. 2022A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementaritycited by 22
  17. 2023The Impact of Imperfect XAI on Human-AI Decision-Makingcited by 21
  18. 2023Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressurecited by 17
  19. 2023Diverse Conventions for Human-AI Collaborationcited by 14
  20. 2020Do I Look Like a Criminal? Examining how Race Presentation Impacts Human Judgement of Recidivismcited by 11
  21. 2020Human vs. supervised machine learning: Who learns patterns faster?cited by 9
  22. 2021Human-level COVID-19 Diagnosis from Low-dose CT Scans Using a Two-stage Time-distributed Capsule Networkcited by 6
  23. 2023ML-Based Teaching Systems: A Conceptual Frameworkcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 12; 2026: 20.

35 papers.

Sort:

By area:

  1. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
  2. 2025CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Codingcited by 11
  3. 2024Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaborationcited by 8
  4. 2025Towards Human-AI Complementarity in Matching Taskscited by 7
  5. 2026AI Agents for Inventory Control: Human-LLM-OR Complementaritycited by 6
  6. 2026Epistemology gives a Future to Complementarity in Human-AI Interactionscited by 5
  7. 2026Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Liftcited by 4
  8. 2026Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Humancited by 3
  9. 2025When Bias Backfires: The Modulatory Role of Counterfactual Explanations on the Adoption of Algorithmic Bias in XAI-Supported Human Decision-Makingcited by 2
  10. 2025No Need for Learning to Defer? A Training Free Deferral Framework to Multiple Experts through Conformal Predictioncited by 2
  11. 2025Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Supportcited by 2
  12. 2024Confidence-weighted integration of human and machine judgments for superior decision-makingcited by 1
23 more
  1. 2025A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AIcited by 1
  2. 2026What Types of Human-AI Teams Exist?cited by 1
  3. 2024An Empirical Examination of the Evaluative AI Frameworkcited by 0
  4. 2025Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptationcited by 0
  5. 2025The safe harbor paradox: when combining human and AI skills creates or destroys valuecited by 0
  6. 2025Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signalscited by 0
  7. 2025ProSEA: Problem Solving via Exploration Agentscited by 0
  8. 2025Development of Mental Models in Human-AI Collaboration: A Conceptual Frameworkcited by 0
  9. 2026Thinking Is Not Telling: Information Disclosure in User-Service LLM Agentscited by 0
  10. 2026Integrating Causal Machine Learning into Clinical Decision Support Systems: Insights from Literature and Practicecited by 0
  11. 2026A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environmentscited by 0
  12. 2026When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guaranteescited by 0
  13. 2026From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Reviewcited by 0
  14. 2026Addressing the Synergy Gap: The Six Elements of the Design Spacecited by 0
  15. 2026AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?cited by 0
  16. 2026Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactionscited by 0
  17. 2026SCAN: A Decision-Making Framework for Effective Task Allocation with Generative AIcited by 0
  18. 2026Align AI to Dynamic Human-AI Workflowscited by 0
  19. 2026Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaborationcited by 0
  20. 2026Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guaranteescited by 0
  21. 2026Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systemscited by 0
  22. 2026Available but Unclaimed: An Empirical Study of Human-AI Synergycited by 0
  23. 2026Should I stay or should I show? Learning to selectively disclose informationcited by 0