← Search

Itamar Pres

2 accepted papers

2026

Position: It’s Time to Optimize for Self-Consistency

ICML 2026poster

Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing (“sycophancy”), exhibit incomplete logical generalization, and produce confident but incorrect responses. We argue that these failures…

Cited by 0SourceScholar
2024

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity

ICML 2024oral

While alignment algorithms are commonly used to tune pre-trained language models towards user preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain phenomena like jailbreaks. In this work we study a popular algorithm,…