Natural Language Generation Challenges for Explainable AI
This work addresses the problem of improving explainable AI for users by outlining research challenges, but it is incremental as it synthesizes existing issues without introducing new methods or data.
The paper identifies key challenges in generating high-quality explanations for AI systems from a Natural Language Generation perspective, focusing on aspects like purpose, audience targeting, narrative structure, and uncertainty handling, without presenting specific results or numbers.
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.