Natural Language Generation Challenges for Explainable AI
Not on the map. Why?
Abstract (arXiv)
Good quality explanations of artificial intelligence (XAI) reasoning must be written (and evaluated) for an explanatory purpose, targeted towards their readers, have a good narrative and causal structure, and highlight where uncertainty and data quality affect the AI output. I discuss these challenges from a Natural Language Generation (NLG) perspective, and highlight four specific NLG for XAI research challenges.
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 4; 2023: 3; 2024: 1.
10 papers.
- 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 175
- 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
- 2023Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledgecited by 32
- 2023The role of causality in explainable artificial intelligencecited by 17
- 2022Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methodscited by 13
- 2022Mediators: Conversational Agents Explaining NLP Model Behaviorcited by 7
- 2022Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Reviewcited by 3
- 2023Evaluation of Human-Understandability of Global Model Explanations using Decision Treecited by 2
- 2021CrystalCandle: A User-Facing Model Explainer for Narrative Explanationscited by 1
- 2024Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Modelscited by 0
- 2024Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models31 Jan 2024
- 2023Evaluation of Human-Understandability of Global Model Explanations using Decision Tree18 Sep 2023
- 2023The role of causality in explainable artificial intelligence18 Sep 2023
- 2023Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge10 May 2023
- 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning15 Dec 2022
- 2022Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review7 Dec 2022
- 2022Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods13 Oct 2022
- 2022Mediators: Conversational Agents Explaining NLP Model Behavior13 Jun 2022
- 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities11 Nov 2021
- 2021CrystalCandle: A User-Facing Model Explainer for Narrative Explanations27 May 2021