# Contrastive Explanations of Plans Through Model Restrictions

arXiv: https://arxiv.org/abs/2103.15575 · HTML: https://mlsanity.com/paper/2103.15575/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 74 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 16 of 16)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Explainable Reinforcement Learning Through a Causal Lens](https://mlsanity.com/paper/1905.10958/) (2019)
- [Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences](https://mlsanity.com/paper/1712.00547/) (2017)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI](https://mlsanity.com/paper/1902.01876/) (2019)
- [Explainable Planning](https://mlsanity.com/paper/1709.10256/) (2017)
- [Plan Explicability and Predictability for Robot Task Planning](https://mlsanity.com/paper/1511.08158/) (2015)
- [Towards Providing Explanations for AI Planner Decisions](https://mlsanity.com/paper/1810.06338/) (2018)
- [Plan Explanations as Model Reconciliation -- An Empirical Study](https://mlsanity.com/paper/1802.01013/) (2018)
- [Generating Justifications for Norm-Related Agent Decisions](https://mlsanity.com/paper/1911.00226/) (2019)
- [Toward Foraging for Understanding of StarCraft Agents: An Empirical Study](https://mlsanity.com/paper/1711.08019/) (2017)
- [Why Couldn't You do that? Explaining Unsolvability of Classical Planning Problems in the Presence of Plan Advice](https://mlsanity.com/paper/1903.08218/) (2019)
- [Towards Contrastive Explanations for Comparing the Ethics of Plans](https://mlsanity.com/paper/2006.12632/) (2020)

## Built on by (most cited first, 16 of 16)

- [Logic-Based Explainability in Machine Learning](https://mlsanity.com/paper/2211.00541/) (2022)
- [Diagnosing AI Explanation Methods with Folk Concepts of Behavior](https://mlsanity.com/paper/2201.11239/) (2022)
- [Counterfactual Influence in Markov Decision Processes](https://mlsanity.com/paper/2402.08514/) (2024)
- [Contrastive Explanations of Centralized Multi-agent Optimization Solutions](https://mlsanity.com/paper/2308.05984/) (2023)
- [On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2510.12201/) (2025)
- [Counting and Reasoning with Plans](https://mlsanity.com/paper/2502.00145/) (2025)
- [Understanding a Robot's Guiding Ethical Principles via Automatically Generated Explanations](https://mlsanity.com/paper/2206.10038/) (2022)
- [On Generating Monolithic and Model Reconciling Explanations in Probabilistic Scenarios](https://mlsanity.com/paper/2405.19229/) (2024)
- [i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler](https://mlsanity.com/paper/2607.05888/) (2026)
- [A User Study on Contrastive Explanations for Multi-Effector Temporal Planning with Non-Stationary Costs](https://mlsanity.com/paper/2409.13427/) (2024)
- [Preprint: Exploring Inevitable Waypoints for Unsolvability Explanation in Hybrid Planning Problems](https://mlsanity.com/paper/2504.15668/) (2025)
- [Counterfactual Scenarios for Automated Planning](https://mlsanity.com/paper/2508.21521/) (2025)
- [Ontological foundations for contrastive explanatory narration of robot plans](https://mlsanity.com/paper/2509.22493/) (2025)
- [Contrastive explanations of BDI agents](https://mlsanity.com/paper/2602.13323/) (2026)
- [Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning](https://mlsanity.com/paper/2603.02070/) (2026)
- ["Why This Avoidance Maneuver?" Contrastive Explanations in Human-Supervised Maritime Autonomous Navigation](https://mlsanity.com/paper/2604.08032/) (2026)

## Abstract (arXiv)

In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user's expectation. We frame Explainable AI Planning in the context of the plan negotiation problem, in which a succession of hypothetical planning problems are generated and solved. The object of the negotiation is for the user to understand and ultimately arrive at a satisfactory plan. We present the results of a user study that demonstrates that when users ask questions about plans, those questions are contrastive, i.e. "why A rather than B?". We use the data from this study to construct a taxonomy of user questions that often arise during plan negotiation. We formally define our approach to plan negotiation through model restriction as an iterative process. This approach generates hypothetical problems and contrastive plans by restricting the model through constraints implied by user questions. We formally define model-based compilations in PDDL2.1 of each constraint derived from a user question in the taxonomy, and empirically evaluate the compilations in terms of computational complexity. The compilations were implemented as part of an explanation framework that employs iterative model restriction. We demonstrate its benefits in a second user study.