PAP
NLG Evaluation: Past, Present, Future
May 22, 2026
Abstract
Natural Language Generation (NLG) evaluation has changed dramatically since 1990, and will continue to evolve in the future. In 1990, when NLG had close ties to linguistics, there was very little formal experimental evaluation in the modern sense. In 2026, when NLG is closely linked to machine learning, experimental evaluation is expected and indeed fundamental to research. Many evaluation techniques were developed over this period, including most recently LLM-as-Judge. I expect NLG evaluation will continue to evolve in the future. In particular, impact, qualitative, and safety evaluation will become more important as large numbers of people routinely use NLG technology.
Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Ehud Reiter
Your notes (browser-local)
savedCross-links
arXiv:2605.23715