Author

Ari Holtzman

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Can LLMs Anticipate Their Cruxes?

To use language models to help us make decisions we would like to understand the rationale behind the language model's outputs. In principle, the language model provides its rationale as part of its text output. However, the sheer volume of text makes this hard to use in practice. In this paper, we are interested in ex...

David Reber, James Reber, Ari Holtzman et al. · 0 citations

#artificial intelligence Preprint Jun 2025

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon

These findings establish BF as a diagnostic for understanding and controlling LLM outputs, clarifying how alignment reduces variability, CoT stabilizes generation, and base models can be steered away from diversity.

Chenghao Yang, Si-Da Li, Ari Holtzman · 24 citations · ⚡4