Unpacking Interpretability: Human-Centered Criteria for Optimal Combinatorial Solutions

Researchers developed a framework to identify what makes AI-generated optimal solutions more interpretable to humans, focusing on bin-packing problems. The study found that humans prefer solutions with three key properties: alignment with greedy heuristics, simple within-bin composition, and ordered visual representation.

• →Human preferences for AI solutions reliably track three quantifiable properties: heuristic alignment, compositional simplicity, and ordered representation.
• →Ordered visual representations and alignment with greedy heuristics showed the strongest associations with human interpretability preferences.
• →The research provides actionable criteria for designing interpretability-aware optimization systems.
• →Mixed reaction-time evidence suggests faster responses primarily when heuristic differences are larger between solutions.
• →The findings enable quantification of trade-offs between optimality and interpretability in real-world applications.