Ari Holtzman
Source-listed: Assistant Professor of Computer Science and Data Science; PI/Head of Conceptualization Lab · University of Chicago
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- QLoRA: Efficient Finetuning of Quantized LLMsSaved credit: Contributor · 2023Explore people connected to this work →
- The Curious Case of Neural Text DegenerationSaved credit: First author · 2020Explore people connected to this work →
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?Saved credit: Contributor · 2022Explore people connected to this work →
- Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?Saved credit: First author · 2023Explore people connected to this work →
- Prompting as Scientific InquirySaved credit: First author · 2025Explore people connected to this work →