← Authors

Ari Holtzman

34 papers · 2017–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (8) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (73) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (14) 🌍 Conference Polyglot (9) 🀝 Dynamic Duo (22) 🧬 Topic Evolution πŸ† Keyword Champion (3) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (159) ⚑ Prolific Year (7) ❓ The Questioner (4) πŸ”₯ Unstoppable (9) πŸ’Ž Century Club (34)

Conferences

EMNLP (8) ACL (7) ICLR (5) IJCNLP (4) NIPS (4) NAACL (3) AAAI (1) CVPR (1) EACL (1)

Top co-authors

Yejin Choi (22) Luke Zettlemoyer (8) Ali Farhadi (6) Chandra Bhagavatula (5) Rowan Zellers (5) Jan Buys (5) Peter West (5) Antoine Bosselut (5) Yonatan Bisk (4) Elizabeth Clark (4)

Research topics

Linguistics (1)

Keywords

language model (11) large language model (6) text generation (5) unsupervised learning (4) decoding algorithm (3) abstractive summarization (2) natural language processing (2) story generation (2) language understanding (2) zero-shot learning (2) language grounding (2) language generation (2) information bottleneck (2) self-supervised learning (2) few-shot learning (2) narrative understanding (2) extractive summarization (2) multimodal learning (2) paraphrase generation (2) counterfactual reasoning (2)

Papers

Forking Paths in Neural Text Generation ICLR 2025
MUSE: Machine Unlearning Six-Way Evaluation for Language Models ICLR 2025
Byte Latent Transformer: Patches Scale Better Than Tokens ACL 2025
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass NIPS 2024
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution NIPS 2024
Toward Human Readable Prompt Tuning: Kubrick’s The Shining is a good movie, and a good prompt too? EMNLP 2023
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey ACL 2023
Contrastive Decoding: Open-ended Text Generation as Optimization ACL 2023
QLoRA: Efficient Finetuning of Quantized LLMs NIPS 2023
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? EMNLP 2022
DEMix Layers: Disentangling Domains for Modular Language Modeling NAACL 2022
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World ACL 2021
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World IJCNLP 2021
Discourse Understanding and Factual Consistency in Abstractive Summarization EACL 2021
Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models IJCNLP 2021
Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models ACL 2021
TuringAdvice: A Generative and Dynamic Evaluation of Language Use NAACL 2021
MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations AAAI 2021
Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right EMNLP 2021
CLIPScore: A Reference-free Evaluation Metric for Image Captioning EMNLP 2021
Experience Grounds Language EMNLP 2020
Abductive Commonsense Reasoning ICLR 2020
The Curious Case of Neural Text Degeneration ICLR 2020
HellaSwag: Can a Machine Really Finish Your Sentence? ACL 2019
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle IJCNLP 2019
Counterfactual Story Reasoning and Generation IJCNLP 2019
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation CVPR 2019
Defending Against Neural Fake News NIPS 2019
Counterfactual Story Reasoning and Generation EMNLP 2019
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle EMNLP 2019
Learning to Write with Cooperative Discriminators ACL 2018
Sounding Board: A User-Centric and Content-Driven Social Chatbot NAACL 2018
Simulating Action Dynamics with Neural Process Networks ICLR 2018
Connotation Frames of Power and Agency in Modern Films EMNLP 2017