mlsanityData to 7 Oct 2026

Explaining and Improving Information Complementarities in Multi-Agent Decision-making

arXiv 2502.06152 ↗First posted 10 Feb 2025cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Multiple agents are increasingly combined to make decisions with the expectation of achieving complementary performance, where the decisions they make together outperform those made individually. However, knowing how to improve the performance of collaborating agents requires knowing what information and strategies each agent employs. With a focus on human-AI pairings, we contribute a decision-theoretic framework for characterizing the value of information. By defining complementary information, our approach identifies opportunities for agents to better exploit available information in AI-assisted decision workflows. We present a novel explanation technique (ILIV-SHAP) that adapts SHAP explanations to highlight human-complementing information. We validate the effectiveness of our framework and ILIV-SHAP through a study of human-AI decision-making, and demonstrate the framework on examples from chest X-ray diagnosis and deepfake detection. We find that presenting ILIV-SHAP with AI predictions leads to reliably greater reductions in error over non-AI assisted decisions more than vanilla SHAP.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 43 of its 83 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

43 of 83 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  8. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  9. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  10. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
  11. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  12. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 228
31 more
  1. 2018On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detectioncited by 159
  2. 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 138
  3. 2020Learning to Complement Humanscited by 123
  4. 2019The Algorithmic Automation Problem: Prediction, Triage, and Human Effortcited by 101
  5. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 100
  6. 2021Differentiable Learning Under Triagecited by 74
  7. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  8. 2021Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowdscited by 58
  9. 2022Improving Expert Predictions with Conformal Predictioncited by 54
  10. 2023U-Calibration: Forecasting for an Unknown Agentcited by 46
  11. 2021Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactionscited by 35
  12. 2021Role of Human-AI Interaction in Selective Predictioncited by 33
  13. 2022A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Makingcited by 29
  14. 2020Optimization of Scoring Rulescited by 28
  15. 2023Human-Aligned Calibration for AI-Assisted Decision Makingcited by 28
  16. 2024A Decision Theoretic Framework for Measuring AI Reliancecited by 26
  17. 2023When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programmingcited by 25
  18. 2024Towards Human-AI Complementarity with Prediction Setscited by 25
  19. 2024Forecasting for Swap Regret for All Downstream Agentscited by 24
  20. 2022A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementaritycited by 22
  21. 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboardingcited by 20
  22. 2022Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservablescited by 19
  23. 2022On the Effect of Information Asymmetry in Human-AI Teamscited by 17
  24. 2023Auditing for Human Expertisecited by 12
  25. 2022Designing Closed Human-in-the-loop Deferral Pipelinescited by 11
  26. 2022Algorithmic Assistance with Recommendation-Dependent Preferencescited by 11
  27. 2023The Rational Agent Benchmark for Data Visualizationcited by 10
  28. 2017Informational Substitutescited by 7
  29. 2024Does AI help humans make better decisions? A statistical evaluation framework for experimental and observational studiescited by 7
  30. 2019Measuring the Completeness of Theoriescited by 6
  31. 2021To design interfaces for exploratory data analysis, we need theories of graphical inferencecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Human-AI Collaborative Uncertainty Quantificationcited by 6
  2. 2025Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translationcited by 5
  3. 2025Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Modelscited by 1
  4. 2025One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Makingcited by 0
  5. 2026Toward Human-AI Complementarity Across Diverse Taskscited by 0
  6. 2026Addressing the Synergy Gap: The Six Elements of the Design Spacecited by 0