A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations
Not on the map. Why?
Abstract (arXiv)
Effective AI governance requires structured approaches for stakeholders to access and verify AI system behavior. With the rise of large language models, Natural Language Explanations (NLEs) are now key to articulating model behavior, which necessitates a focused examination of their characteristics and governance implications. We draw on Explainable AI (XAI) literature to create an updated XAI taxonomy, adapted to prompt-based NLEs, across three dimensions: (1) Context, including task, data, audience, and goals; (2) Generation and Presentation, covering generation methods, inputs, interactivity, outputs, and forms; and (3) Evaluation, focusing on content, presentation, and user-centered properties, as well as the setting of the evaluation. This taxonomy provides a framework for researchers, auditors, and policymakers to characterize, design, and enhance NLEs for transparent AI systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 11 Jul 2025.
Builds on
29 of 43 references.
References · 29
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
- 2024A Survey on LLM-as-a-Judgecited by 1,423
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
- 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
- 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
- 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
- 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 344
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
- 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
- 2018Manipulating and Measuring Model Interpretabilitycited by 256
17 more
- 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 254
- 2018Techniques for Interpretable Machine Learningcited by 238
- 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
- 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
- 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
- 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 106
- 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 91
- 2023Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanationscited by 73
- 2022NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Taskscited by 60
- 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
- 2024Open Problems in Technical AI Governancecited by 49
- 2018Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systemscited by 48
- 2022Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AIcited by 40
- 2017Automatic Generation of Natural Language Explanationscited by 22
- 2022Machine Explanations and Human Understandingcited by 20
- 2023Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressurecited by 17
- 2024Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Settingcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.