# Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience

arXiv: https://arxiv.org/abs/2001.09219 · HTML: https://mlsanity.com/paper/2001.09219/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2020.

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

- [Human-Centered Explainable AI (XAI): From Algorithms to User Experiences](https://mlsanity.com/paper/2110.10790/) (2021)
- [Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies](https://mlsanity.com/paper/2112.11471/) (2021)
- [Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations](https://mlsanity.com/paper/2301.07255/) (2023)
- [Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation](https://mlsanity.com/paper/2204.11788/) (2022)
- [Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making](https://mlsanity.com/paper/2101.05303/) (2021)
- [ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing](https://mlsanity.com/paper/2305.09770/) (2023)
- [Selective Explanations: Leveraging Human Input to Align Explainable AI](https://mlsanity.com/paper/2301.09656/) (2023)
- [Soliciting Human-in-the-Loop User Feedback for Interactive Machine Learning Reduces User Trust and Impressions of Model Accuracy](https://mlsanity.com/paper/2008.12735/) (2020)
- [A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification](https://mlsanity.com/paper/2109.11301/) (2021)
- [Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations](https://mlsanity.com/paper/2101.09498/) (2021)
- [Facilitating Knowledge Sharing from Domain Experts to Data Scientists for Building NLP Models](https://mlsanity.com/paper/2102.00036/) (2021)
- [Perspectives on Incorporating Expert Feedback into Model Updates](https://mlsanity.com/paper/2205.06905/) (2022)
- [Mediators: Conversational Agents Explaining NLP Model Behavior](https://mlsanity.com/paper/2206.06029/) (2022)
- [User Driven Model Adjustment via Boolean Rule Explanations](https://mlsanity.com/paper/2203.15071/) (2022)
- [Class Introspection: A Novel Technique for Detecting Unlabeled Subclasses by Leveraging Classifier Explainability Methods](https://mlsanity.com/paper/2107.01657/) (2021)
- [A Human-ML Collaboration Framework for Improving Video Content Reviews](https://mlsanity.com/paper/2210.09500/) (2022)
- [Towards Fair and Explainable AI using a Human-Centered AI Approach](https://mlsanity.com/paper/2306.07427/) (2023)
- [Fine-tuning of explainable CNNs for skin lesion classification based on dermatologists' feedback towards increasing trust](https://mlsanity.com/paper/2304.01399/) (2023)
- [An Empirical Examination of the Evaluative AI Framework](https://mlsanity.com/paper/2411.08583/) (2024)
- [Human-in-the-Loop User Feedback Affects Perceived Accuracy and Trust, but Task Subjectivity Matters](https://mlsanity.com/paper/2607.17548/) (2026)

## Abstract (arXiv)

The wide adoption of Machine Learning technologies has created a rapidly growing demand for people who can train ML models. Some advocated the term "machine teacher" to refer to the role of people who inject domain knowledge into ML models. One promising learning paradigm is Active Learning (AL), by which the model intelligently selects instances to query the machine teacher for labels. However, in current AL settings, the human-AI interface remains minimal and opaque. We begin considering AI explanations as a core element of the human-AI interface for teaching machines. When a human student learns, it is a common pattern to present one's own reasoning and solicit feedback from the teacher. When a ML model learns and still makes mistakes, the human teacher should be able to understand the reasoning underlying the mistakes. When the model matures, the machine teacher should be able to recognize its progress in order to trust and feel confident about their teaching outcome. Toward this vision, we propose a novel paradigm of explainable active learning (XAL), by introducing techniques from the recently surging field of explainable AI (XAI) into an AL setting. We conducted an empirical study comparing the model learning outcomes, feedback content and experience with XAL, to that of traditional AL and coactive learning (providing the model's prediction without the explanation). Our study shows benefits of AI explanation as interfaces for machine teaching--supporting trust calibration and enabling rich forms of teaching feedback, and potential drawbacks--anchoring effect with the model judgment and cognitive workload. Our study also reveals important individual factors that mediate a machine teacher's reception to AI explanations, including task knowledge, AI experience and need for cognition. By reflecting on the results, we suggest future directions and design implications for XAL.