Ari Holtzman
30 papers · 2017–2025 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (70) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π¬
Deep Specialist
(11)
π€
Dynamic Duo
(18)
π§¬
Topic Evolution
π
Keyword Champion
(3)
π§
Keyword Pioneer
β‘
Prolific Year Β· Productive
π
Trend Setter
π₯
Unstoppable Β· Bronze
β
The Questioner
(4)
ποΈ
Keyword Collector
(169)
π
Conference Pioneer
π
Renaissance Researcher
(5)
π
Century Club Β· Bronze
Top co-authors
Research topics
Natural Language Processing
(22)
Artificial Intelligence
(19)
Machine Learning
(19)
Core AI
(18)
Deep Learning
(16)
Generation
(14)
Learning Types Β· Machine Learning
(13)
Models
(12)
Applications
(7)
Learning Types Β· Deep Learning
(6)
Optimization & Theory
(6)
Resources & Methods
(5)
Interdisciplinary
(4)
Application Areas
(4)
Core Methods
(4)
Keywords
language model
(10)
text generation
(7)
large language model
(6)
decoding algorithm
(3)
neural network
(2)
zero-shot learning
(2)
few-shot learning
(2)
unsupervised learning
(2)
commonsense reasoning
(2)
natural language processing
(2)
multimodal learning
(2)
natural language inference
(2)
language understanding
(2)
natural language generation
(2)
abstractive summarization
(2)
knowledge distillation
(1)
self-supervised learning
(1)
adversarial learning
(1)
information bottleneck
(1)
text classification
(1)
Papers
Byte Latent Transformer: Patches Scale Better Than Tokens
ACL 2025
Forking Paths in Neural Text Generation
ICLR 2025
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
ICLR 2025
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
NeurIPS 2024
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
NeurIPS 2024
Contrastive Decoding: Open-ended Text Generation as Optimization
ACL 2023
QLoRA: Efficient Finetuning of Quantized LLMs
NeurIPS 2023
Toward Human Readable Prompt Tuning: Kubrickβs 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
DEMix Layers: Disentangling Domains for Modular Language Modeling
NAACL 2022
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
EMNLP 2022
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
EMNLP 2021
Discourse Understanding and Factual Consistency in Abstractive Summarization
EACL 2021
MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations
AAAI 2021
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World
ACL 2021
Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models
ACL 2021
Surface Form Competition: Why the Highest Probability Answer Isnβt Always Right
EMNLP 2021
TuringAdvice: A Generative and Dynamic Evaluation of Language Use
NAACL 2021
Abductive Commonsense Reasoning
ICLR 2020
Experience Grounds Language
EMNLP 2020
The Curious Case of Neural Text Degeneration
ICLR 2020
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle
EMNLP 2019
Counterfactual Story Reasoning and Generation
EMNLP 2019
Defending Against Neural Fake News
NeurIPS 2019
HellaSwag: Can a Machine Really Finish Your Sentence?
ACL 2019
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation
CVPR 2019
Learning to Write with Cooperative Discriminators
ACL 2018
Simulating Action Dynamics with Neural Process Networks
ICLR 2018
Sounding Board: A User-Centric and Content-Driven Social Chatbot
NAACL 2018
Connotation Frames of Power and Agency in Modern Films
EMNLP 2017