← Search

Jonathan Rawski

2 accepted papers

2026

Probability Distributions Computed by Autoregressive Transformers

ICLR 2026poster

Most expressivity results for transformers treat them as language recognizers (which accept or reject strings), and not as they are used in practice, as language models (which generate strings autoregressively and probabilistically). We characterize the probability distributions that transformer lan…

Cited by 0SourceScholar
2022

Benchmarking Compositionality with Formal Languages

COLING 2022main

Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large neural models in NLP acquire this ability while learning from data is an open question. In this paper, we look at this problem from the perspective of formal languages.…