# Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selection

arXiv: https://arxiv.org/abs/2504.03744 · HTML: https://mlsanity.com/paper/2504.03744/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Bayesian optimization for materials design](https://mlsanity.com/paper/1506.01349/) (2015)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- [Preferential Bayesian Optimization](https://mlsanity.com/paper/1704.03651/) (2017)
- [Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision support](https://mlsanity.com/paper/2302.12389/) (2023)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes](https://mlsanity.com/paper/2203.11382/) (2022)
- [Looping in the Human Collaborative and Explainable Bayesian Optimization](https://mlsanity.com/paper/2310.17273/) (2023)
- [Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations](https://mlsanity.com/paper/2112.09669/) (2021)
- [Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models](https://mlsanity.com/paper/2305.15167/) (2023)
- [Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration](https://mlsanity.com/paper/2403.04629/) (2024)
- [Explainable AI improves task performance in human-AI collaboration](https://mlsanity.com/paper/2406.08271/) (2024)
- [Challenging common interpretability assumptions in feature attribution explanations](https://mlsanity.com/paper/2012.02748/) (2020)
- [Explainable Bayesian Optimization](https://mlsanity.com/paper/2401.13334/) (2024)
- [A Corrected Expected Improvement Acquisition Function Under Noisy Observations](https://mlsanity.com/paper/2310.05166/) (2023)

## Built on by (most cited first, 2 of 2)

- [PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations](https://mlsanity.com/paper/2603.06485/) (2026)
- [DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization](https://mlsanity.com/paper/2512.14263/) (2025)

## Abstract (arXiv)

This paper introduces Multi-Output LOcal Narrative Explanation (MOLONE), a novel comparative explanation method designed to enhance preference selection in human-in-the-loop Preference Bayesian optimization (PBO). The preference elicitation in PBO is a non-trivial task because it involves navigating implicit trade-offs between vector-valued outcomes, subjective priorities of decision-makers, and decision-makers' uncertainty in preference selection. Existing explainable AI (XAI) methods for BO primarily focus on input feature importance, neglecting the crucial role of outputs (objectives) in human preference elicitation. MOLONE addresses this gap by providing explanations that highlight both input and output importance, enabling decision-makers to understand the trade-offs between competing objectives and make more informed preference selections. MOLONE focuses on local explanations, comparing the importance of input features and outcomes across candidate samples within a local neighborhood of the search space, thus capturing nuanced differences relevant to preference-based decision-making. We evaluate MOLONE within a PBO framework using benchmark multi-objective optimization functions, demonstrating its effectiveness in improving convergence compared to noisy preference selections. Furthermore, a user study confirms that MOLONE significantly accelerates convergence in human-in-the-loop scenarios by facilitating more efficient identification of preferred options.