Unpacking Interpretability: Human-Centered Criteria for Optimal Combinatorial Solutions

2026-03-09

AI Summary

This study addresses the challenge of human–algorithm collaboration when optimization algorithms yield multiple equally optimal solutions, a scenario hindered by the lack of a clear definition of human-interpretable differences among such solutions. Through a behavioral experiment in which participants selected the more understandable option between two equivalent bin-packing solutions, the authors combined response times, eye-tracking data, and structural feature quantification to identify three key structural attributes of interpretability: alignment with greedy heuristics, simplicity of intra-bin composition, and orderliness of visual representation. The findings reveal that orderly visual representation and alignment with heuristic strategies most strongly influence human preference, while compositional simplicity also shows consistent effects. These results provide actionable insights for designing optimization systems that jointly achieve optimality and human interpretability in real-world applications.

Technology Category

• Search and Optimization: Algorithm Configuration
• Humans and AI: Learning Human Values and Preferences
• Knowledge Representation and Reasoning: Preferences

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Algorithmic support systems often return optimal solutions that are hard to understand. Effective human-algorithm collaboration, however, requires interpretability. When machine solutions are equally optimal, humans must select one, but a precise account of what makes one solution more interpretable than another remains missing. To identify structural properties of interpretable machine solutions, we present an experimental paradigm in which participants chose which of two equally optimal solutions for packing items into bins was easier to understand. We show that preferences reliably track three quantifiable properties of solution structure: alignment with a greedy heuristic, simple within-bin composition, and ordered visual representation. The strongest associations were observed for ordered representations and heuristic alignment, with compositional simplicity also showing a consistent association. Reaction-time evidence was mixed, with faster responses observed primarily when heuristic differences were larger, and aggregate webcam-based gaze did not show reliable effects of complexity. These results provide a concrete, feature-based account of interpretability in optimal packing solutions, linking solution structure to human preference. By identifying actionable properties (simple compositions, ordered representation, and heuristic alignment), our findings enable interpretability-aware optimization and presentation of machine solutions, and outline a path to quantify trade-offs between optimality and interpretability in real-world allocation and design tasks.

Problem

• interpretability
• combinatorial optimization
• human-algorithm collaboration
• solution preference
• packing problem

Innovation

• interpretability
• combinatorial optimization
• human-centered AI
• heuristic alignment
• solution structure