# Natural Language Generation Challenges for Explainable AI

arXiv: https://arxiv.org/abs/1911.08794 · HTML: https://mlsanity.com/paper/1911.08794/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 10 of 10)

- [ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning](https://mlsanity.com/paper/2212.07919/) (2022)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge](https://mlsanity.com/paper/2305.05976/) (2023)
- [The role of causality in explainable artificial intelligence](https://mlsanity.com/paper/2309.09901/) (2023)
- [Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods](https://mlsanity.com/paper/2210.07222/) (2022)
- [Mediators: Conversational Agents Explaining NLP Model Behavior](https://mlsanity.com/paper/2206.06029/) (2022)
- [Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review](https://mlsanity.com/paper/2212.03747/) (2022)
- [Evaluation of Human-Understandability of Global Model Explanations using Decision Tree](https://mlsanity.com/paper/2309.09917/) (2023)
- [CrystalCandle: A User-Facing Model Explainer for Narrative Explanations](https://mlsanity.com/paper/2105.12941/) (2021)
- [Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models](https://mlsanity.com/paper/2401.17511/) (2024)

## 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.