DeCoDe: Defer-and-Complement Decision-Making via Decoupled Concept Bottleneck Models

2025/05/25 by He, Chengbo, Zou, Bochao, Xing, Junliang +3 · 1 citation
#Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2505.19220

Abstract

In human-AI collaboration, a central challenge is deciding whether the AI should handle a task, be deferred to a human expert, or be addressed through collaborative effort. Existing Learning to Defer approaches typically make binary choices between AI and humans, neglecting their complementary strengths. They also lack interpretability, a critical property in high-stakes scenarios where users must understand and, if necessary, correct the model's reasoning. To overcome these limitations, we propose Defer-and-Complement Decision-Making via Decoupled Concept Bottleneck Models (DeCoDe), a concept-driven framework for human-AI collaboration. DeCoDe makes strategy decisions based on human-interpretable concept representations, enhancing transparency throughout the decision process. It supports three flexible modes: autonomous AI prediction, deferral to humans, and human-AI collaborative complementarity, selected via a gating network that takes concept-level inputs and is trained using a novel surrogate loss that balances accuracy and human effort. This approach enables instance-specific, interpretable, and adaptive human-AI collaboration. Experiments on real-world datasets demonstrate that DeCoDe significantly outperforms AI-only, human-only, and traditional deferral baselines, while maintaining strong robustness and interpretability even under noisy expert annotations.

Citations

• Learning to Help in Multi-Class Settings
• Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents
• How human–AI feedback loops alter human perceptual, emotional and social judgements
• Coverage-Constrained Human-AI Cooperation with Multiple Experts
• Tree-Based Leakage Inspection and Control in Concept Bottleneck Models
• Learning to Complement and to Defer to Multiple Users
• Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
• Using AI Uncertainty Quantification to Improve Human Decision-Making
• When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-making
• Who Should Predict? Exact Algorithms For Learning to Defer to Humans
• Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles
• Calibrated Learning to Defer with One-vs-All Classifiers
• Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches
• Concept Bottleneck Models
• Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
• Consistent Estimators for Learning to Defer to an Expert
• Learning to Complement Humans
• OPTIMAM Mammography Image Database: a large scale resource of mammography images and clinical data
• The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
• Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
• Deep Residual Learning for Image Recognition
• Rethinking the Inception Architecture for Computer Vision
• Deep Learning Face Attributes in the Wild

Cited by

• MARPO: A Reflective Policy Optimization for Multi Agent Reinforcement Learning

Related

• Human-AI Collaboration in Decision-Making: Beyond Learning to Defer
• The Impact of Concept Explanations and Interventions on Human-Machine Collaboration
• Learning to Complement and to Defer to Multiple Users
• Learning Complementary Policies for Human-AI Teams
• Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making