# Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills

arXiv: https://arxiv.org/abs/2410.04253 · HTML: https://mlsanity.com/paper/2410.04253/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 105 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 30 of 45)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems](https://mlsanity.com/paper/2001.08298/) (2020)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies](https://mlsanity.com/paper/2007.15911/) (2020)
- [Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations](https://mlsanity.com/paper/2302.02187/) (2023)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- ["I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust](https://mlsanity.com/paper/2405.00623/) (2024)
- [TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations](https://mlsanity.com/paper/2207.04154/) (2022)
- [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)
- [One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency](https://mlsanity.com/paper/2001.09734/) (2020)
- [Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning](https://mlsanity.com/paper/2202.05402/) (2022)
- [Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes](https://mlsanity.com/paper/2310.10648/) (2023)
- [Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong](https://mlsanity.com/paper/2310.12558/) (2023)
- [Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems](https://mlsanity.com/paper/2301.11333/) (2023)
- [Generating Counterfactual Explanations with Natural Language](https://mlsanity.com/paper/1806.09809/) (2018)
- [Improving Human-AI Collaboration With Descriptions of AI Behavior](https://mlsanity.com/paper/2301.06937/) (2023)
- [Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens](https://mlsanity.com/paper/2102.00593/) (2021)
- [Contrastive Explanations with Local Foil Trees](https://mlsanity.com/paper/1806.07470/) (2018)
- [Who Goes First? Influences of Human-AI Workflow on Decision Making in Clinical Imaging](https://mlsanity.com/paper/2205.09696/) (2022)
- [How Knowledge Workers Think Generative AI Will (Not) Transform Their Industries](https://mlsanity.com/paper/2310.06778/) (2023)
- [Teaching Humans When To Defer to a Classifier via Exemplars](https://mlsanity.com/paper/2111.11297/) (2021)
- [Selective Explanations: Leveraging Human Input to Align Explainable AI](https://mlsanity.com/paper/2301.09656/) (2023)

## Built on by (most cited first, 14 of 14)

- [Exploring the Impact of Explainable AI and Cognitive Capabilities on Users' Decisions](https://mlsanity.com/paper/2505.01192/) (2025)
- [From Junior to Senior: Allocating Agency and Navigating Professional Growth in Agentic AI-Mediated Software Engineering](https://mlsanity.com/paper/2602.00496/) (2026)
- [Can Agents Distinguish Visually Hard-to-Separate Diseases in a Zero-Shot Setting? A Pilot Study](https://mlsanity.com/paper/2602.22959/) (2026)
- [More Isn't Always Better: Balancing Decision Accuracy and Conformity Pressures in Multi-AI Advice](https://mlsanity.com/paper/2603.22152/) (2026)
- [An Empirical Examination of the Evaluative AI Framework](https://mlsanity.com/paper/2411.08583/) (2024)
- [Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents](https://mlsanity.com/paper/2506.20062/) (2025)
- [Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI](https://mlsanity.com/paper/2508.07872/) (2025)
- [Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding](https://mlsanity.com/paper/2603.25251/) (2026)
- [Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol](https://mlsanity.com/paper/2608.08882/) (2026)
- [LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions](https://mlsanity.com/paper/2609.14849/) (2026)
- [Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work](https://mlsanity.com/paper/2609.17065/) (2026)
- [When the AI Leaves the Tailorshop: Measuring What an LLM Advisor Leaves Behind in Complex Problem Solving](https://mlsanity.com/paper/2610.00163/) (2026)
- [GFGE: Unifying Explainable AI Methods through an Interpretation Framework](https://mlsanity.com/paper/2610.05225/) (2026)
- [Novice Reliance Calibration in AI-Assisted Decision Making: The Role of Explanations and Self-Assessment](https://mlsanity.com/paper/2610.07800/) (2026)

## Abstract (arXiv)

People's decision-making abilities often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations. We argue this is partly because people intuitively seek contrastive explanations, which clarify the difference between the AI's decision and their own reasoning, while most AI systems offer "unilateral" explanations that justify the AI's decision but do not account for users' thinking. To align human-AI knowledge on decision tasks, we introduce a framework for generating human-centered contrastive explanations that explain the difference between AI's choice and a predicted, likely human choice about the same task. Results from a large-scale experiment (N = 628) demonstrate that contrastive explanations significantly enhance users' independent decision-making skills compared to unilateral explanations, without sacrificing decision accuracy. Amid rising deskilling concerns, our research demonstrates that incorporating human reasoning into AI design can foster human skill development.