CHI 2026Best Paper Award

Interactive Explainable Ranking

Chao Zhang and Abe DavisCornell University

PaperVideoToolCode
Interactive Explainable Ranking teaser figure
In this paper, we formalize explainable ranking as a new problem for decision-making tools: given a set of options, the user needs to find a preferred ranking of those options that is consistent with some weighted combination of simpler or less ambiguous criteria (an explanation). To assist users in explainable ranking, our tool makes the three loops interactive: (1) rank choices, (2) explain with criteria and weights, and (3) identify & resolve conflicts. It visualizes conflicts between the user proposed ranking and the ranking explained by current criteria and weights; allows users to freely edit criteria and weights or add new criteria; and offers User Insertion Sort to safely use uncertain priors (e.g., from AI or optimization) while ensuring that every ranking decision is checked by a human user. We evaluate our system on different ranking tasks reflecting real-world use cases.

Abstract

We propose an interactive decision-making tool for discovering and exploring explainable rankings for a given set of choices (e.g., job offers, vacation destinations, award candidates). We define an explainable ranking as an ordering of choices based on some consistent weighting of measured criteria. Our tool is designed to help users explore different orderings, criteria, and criterion weights in search of an explainable ranking that reflects their own personal preferences. To achieve this, we combine visualization, optimization, and (optionally) the integration of AI to help users identify and correct or explain inconsistencies in their evaluation of different choices. Through user experiments, we demonstrate that our tool leads to more consistent explainable rankings with greater user confidence.

Demo Video

Press

Cornell ChronicleHumans are bad at making complex decisions. AI can call them out.

Citation

@inproceedings{10.1145/3772318.3790810, author = {Zhang, Chao and Davis, Abe}, title = {Interactive Explainable Ranking}, year = {2026}, isbn = {9798400722783}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3772318.3790810}, doi = {10.1145/3772318.3790810}, booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems}, articleno = {619}, numpages = {17}, keywords = {Ranking, Decision-Making}, location = {Barcelona, Spain}, series = {CHI '26} }