A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908449378402304 |
|---|---|
| author | Nejadgholi, Isar Omidyeganeh, Mona Drouin, Marc-Antoine Boisvert, Jonathan |
| author_facet | Nejadgholi, Isar Omidyeganeh, Mona Drouin, Marc-Antoine Boisvert, Jonathan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10585 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations Nejadgholi, Isar Omidyeganeh, Mona Drouin, Marc-Antoine Boisvert, Jonathan Computation and Language Artificial Intelligence 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. |
| title | A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.10585 |