Ari Holtzman8 papers on this site (2018–2022)OpenAlex · ORCID · h-index 22 · 71 works · 7299 citations (openalex-snapshot, 2026-10-14)Profile data from OpenAlex; authors with the same name are not always told apart.Contrastive Decoding: Open-ended Text Generation as OptimizationXiang Lisa Li, Ari Holtzman, Daniel Fried, et al.2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?Sewon Min, Xinxi Lyu, Ari Holtzman, et al.2022CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes, et al.2021Surface Form Competition: Why the Highest Probability Answer Isn't Always RightAri Holtzman, Peter West, Vered Shwartz, et al.2021Experience Grounds LanguageYonatan Bisk, Ari Holtzman, Jesse Thomason, et al.2020Abductive Commonsense ReasoningChandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, et al.2019Defending Against Neural Fake NewsRowan Zellers, Ari Holtzman, Hannah Rashkin, et al.2019Learning to Write with Cooperative DiscriminatorsAri Holtzman, Jan Buys, Maxwell Forbes, et al.2018