# Leveraging Rationales to Improve Human Task Performance

arXiv: https://arxiv.org/abs/2002.04202 · HTML: https://mlsanity.com/paper/2002.04202/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 20 of 20)

- [Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies](https://mlsanity.com/paper/2112.11471/) (2021)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning](https://mlsanity.com/paper/2202.05402/) (2022)
- [In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making](https://mlsanity.com/paper/2305.07722/) (2023)
- [The Who in XAI: How AI Background Shapes Perceptions of AI Explanations](https://mlsanity.com/paper/2107.13509/) (2021)
- [Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery](https://mlsanity.com/paper/2101.01625/) (2021)
- [Rationalization for Explainable NLP: A Survey](https://mlsanity.com/paper/2301.08912/) (2023)
- [Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation](https://mlsanity.com/paper/2109.10149/) (2021)
- [Decoding AI's Nudge: A Unified Framework to Predict Human Behavior in AI-assisted Decision Making](https://mlsanity.com/paper/2401.05840/) (2024)
- [Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems](https://mlsanity.com/paper/2201.04204/) (2022)
- [Experiential Explanations for Reinforcement Learning](https://mlsanity.com/paper/2210.04723/) (2022)
- [How Human-Centered Explainable AI Interface Are Designed and Evaluated: A Systematic Survey](https://mlsanity.com/paper/2403.14496/) (2024)
- [Algorithmic Decision-Making Safeguarded by Human Knowledge](https://mlsanity.com/paper/2211.11028/) (2022)
- [Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations](https://mlsanity.com/paper/2406.19545/) (2024)
- [Incentive-Tuning: Understanding and Designing Incentives for Empirical Human-AI Decision-Making Studies](https://mlsanity.com/paper/2601.15064/) (2026)
- [Underspecified Human Decision Experiments Considered Harmful](https://mlsanity.com/paper/2401.15106/) (2024)
- [Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspective](https://mlsanity.com/paper/2504.10918/) (2025)
- [Explainable Reinforcement Learning Agents Using World Models](https://mlsanity.com/paper/2505.08073/) (2025)
- [A Beautiful Mind: Principles and Strategies for AI-Augmented Human Reasoning](https://mlsanity.com/paper/2503.15530/) (2025)
- [Hybrid Reasoning Systems That Prioritize and Enhance Human Intelligence](https://mlsanity.com/paper/2504.13477/) (2025)

## Abstract (arXiv)

Machine learning (ML) systems across many application areas are increasingly demonstrating performance that is beyond that of humans. In response to the proliferation of such models, the field of Explainable AI (XAI) has sought to develop techniques that enhance the transparency and interpretability of machine learning methods. In this work, we consider a question not previously explored within the XAI and ML communities: Given a computational system whose performance exceeds that of its human user, can explainable AI capabilities be leveraged to improve the performance of the human? We study this question in the context of the game of Chess, for which computational game engines that surpass the performance of the average player are widely available. We introduce the Rationale-Generating Algorithm, an automated technique for generating rationales for utility-based computational methods, which we evaluate with a multi-day user study against two baselines. The results show that our approach produces rationales that lead to statistically significant improvement in human task performance, demonstrating that rationales automatically generated from an AI's internal task model can be used not only to explain what the system is doing, but also to instruct the user and ultimately improve their task performance.