Ari Holtzman

5.3k total citations · 3 hit papers
19 papers, 1.6k citations indexed

About

Ari Holtzman is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Pathology and Forensic Medicine. According to data from OpenAlex, Ari Holtzman has authored 19 papers receiving a total of 1.6k indexed citations (citations by other indexed papers that have themselves been cited), including 18 papers in Artificial Intelligence, 7 papers in Computer Vision and Pattern Recognition and 1 paper in Pathology and Forensic Medicine. Recurrent topics in Ari Holtzman's work include Topic Modeling (16 papers), Natural Language Processing Techniques (14 papers) and Multimodal Machine Learning Applications (6 papers). Ari Holtzman is often cited by papers focused on Topic Modeling (16 papers), Natural Language Processing Techniques (14 papers) and Multimodal Machine Learning Applications (6 papers). Ari Holtzman collaborates with scholars based in United States, United Kingdom and China. Ari Holtzman's co-authors include Yejin Choi, Maxwell Forbes, Jack Hessel, Ronan Le Bras, Yonatan Bisk, Luke Zettlemoyer, Ali Farhadi, Rowan Zellers, Michael Lewis and Hannaneh Hajishirzi and has published in prestigious journals such as Journal of the American Academy of Orthopaedic Surgeons, arXiv (Cornell University) and Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.

In The Last Decade

Ari Holtzman

18 papers receiving 1.6k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

CLIPScore: A Reference-free Evaluation Metric for Image Captioning

2021 392 citations Jack Hessel, Ari Holtzman et al. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing profile →
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

2022 383 citations Sewon Min, Xinxi Lyu et al. profile →
HellaSwag: Can a Machine Really Finish Your Sentence?

2019 332 citations Rowan Zellers, Ari Holtzman et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Ari Holtzman United States	12	1.1k	662	120	54	53	19	1.6k
Minsuk Kahng United States	14	563 0.5×	454 0.7×	228 1.9×	99 1.8×	93 1.8×	41	1.0k
Mennatallah El‐Assady Germany	17	561 0.5×	582 0.9×	77 0.6×	14 0.3×	69 1.3×	92	1.1k
Lizi Liao Singapore	15	713 0.6×	323 0.5×	190 1.6×	38 0.7×	20 0.4×	72	1.0k
Yelong Shen United States	17	1.4k 1.2×	532 0.8×	477 4.0×	63 1.2×	89 1.7×	50	1.8k
Liang Gou United States	18	709 0.6×	435 0.7×	242 2.0×	87 1.6×	56 1.1×	43	1.2k
Fred Hohman United States	12	415 0.4×	332 0.5×	120 1.0×	51 0.9×	60 1.1×	24	808
Dominik Sacha Germany	13	402 0.4×	757 1.1×	56 0.5×	38 0.7×	213 4.0×	27	1.1k
Wenhu Chen United States	19	793 0.7×	344 0.5×	97 0.8×	107 2.0×	40 0.8×	67	1.1k
James Eagan France	12	333 0.3×	675 1.0×	110 0.9×	93 1.7×	127 2.4×	27	1.1k

Countries citing papers authored by Ari Holtzman

Since Specialization

Citations

This map shows the geographic impact of Ari Holtzman's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ari Holtzman with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ari Holtzman more than expected).

Fields of papers citing papers by Ari Holtzman

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Ari Holtzman. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ari Holtzman. The network helps show where Ari Holtzman may publish in the future.

Co-authorship network of co-authors of Ari Holtzman

This figure shows the co-authorship network connecting the top 25 collaborators of Ari Holtzman. A scholar is included among the top collaborators of Ari Holtzman based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Ari Holtzman. Ari Holtzman is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

19 of 19 papers shown

Pagnoni, Artidoro, Ramakanth Pasunuru, Pedro Rodríguez, et al.. (2025). Byte Latent Transformer: Patches Scale Better Than Tokens. 9238–9258. 1 indexed citations

Liu, Yuhan, Hanchen Li, Yuyang Huang, et al.. (2024). CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving. Knowledge@UChicago (University of Chicago). 38–56. 20 indexed citations

Shi, Weijia, Xiaochuang Han, Hila Gonen, et al.. (2023). Toward Human Readable Prompt Tuning: Kubrick’s The Shining is a good movie, and a good prompt too?. 10994–11005. 8 indexed citations

Michael, Julian, Ari Holtzman, Alicia Parrish, et al.. (2023). What Do NLP Researchers Believe? Results of the NLP Community Metasurvey. 16334–16368. 7 indexed citations

Li, Xiang Lisa, Ari Holtzman, Daniel Fried, et al.. (2023). Contrastive Decoding: Open-ended Text Generation as Optimization. 12286–12312. 31 indexed citations

Gururangan, Suchin, Mike Lewis, Ari Holtzman, Noah A. Smith, & Luke Zettlemoyer. (2022). DEMix Layers: Disentangling Domains for Modular Language Modeling. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 5557–5576. 39 indexed citations

Berman, Daniel, et al.. (2022). Comparison of Clinical Guidelines for Authorization of MRI in the Evaluation of Neck Pain and Cervical Radiculopathy in the United States. Journal of the American Academy of Orthopaedic Surgeons. 31(2). 64–70. 1 indexed citations

Min, Sewon, Xinxi Lyu, Ari Holtzman, et al.. (2022). Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?. 11048–11064. 383 indexed citations breakdown →

Hessel, Jack, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, & Yejin Choi. (2021). CLIPScore: A Reference-free Evaluation Metric for Image Captioning. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 7514–7528. 392 indexed citations breakdown →

10.

Forbes, Maxwell, et al.. (2021). MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations. Proceedings of the AAAI Conference on Artificial Intelligence. 35(14). 12760–12767.

11.

Hessel, Jack, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, & Yejin Choi. (2021). CLIPScore: A Reference-free Evaluation Metric for Image Captioning. arXiv (Cornell University). 7514–7528. 1 indexed citations

12.

Gabriel, Saadia, Antoine Bosselut, Ari Holtzman, et al.. (2021). Discourse Understanding and Factual Consistency in Abstractive Summarization. 14 indexed citations

13.

Zellers, Rowan, Ari Holtzman, Elizabeth Clark, et al.. (2020). Evaluating Machines by their Real-World Language Use. arXiv (Cornell University). 5 indexed citations

14.

Holtzman, Ari, et al.. (2020). The Curious Case of Neural Text Degeneration. arXiv (Cornell University). 173 indexed citations

15.

Zellers, Rowan, Ari Holtzman, Yonatan Bisk, Ali Farhadi, & Yejin Choi. (2019). HellaSwag: Can a Machine Really Finish Your Sentence?. 4791–4800. 332 indexed citations breakdown →

16.

Qin, Lianhui, Antoine Bosselut, Ari Holtzman, et al.. (2019). Counterfactual Story Reasoning and Generation. 5042–5052. 56 indexed citations

17.

Ke, Liyiming, Xiujun Li, Yonatan Bisk, et al.. (2019). Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation. 6734–6742. 93 indexed citations

18.

Fang, Hao, Hao Cheng, Maarten Sap, et al.. (2018). Sounding Board: A User-Centric and Content-Driven Social Chatbot. 96–100. 25 indexed citations

19.

Sap, Maarten, et al.. (2017). Connotation Frames of Power and Agency in Modern Films. 2329–2334. 42 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact