Large language models (LLMs) have come closest among all models to date to mastering
human language, yet opinions about their linguistic and cognitive capabilities remain split …

Large language models (LLMs) trained on code-completion have been shown to be capable
of synthesizing simple Python programs from docstrings [1]. We find that these code-writing …

The power of human language and thought arises from systematic compositionality—the
algebraic ability to understand and produce novel combinations from known components …

Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …

In the last year alone, a surge of new benchmarks to measure $\textit {compositional} $
understanding of vision-language models have permeated the machine learning ecosystem …

Large pretrained (eg," foundation") models exhibit distinct capabilities depending on the
domain of data they are trained on. While these domains are generic, they may only barely …

We investigate the ability of language models to perform compositional reasoning tasks
where the overall solution depends on correctly composing the answers to sub-problems …

Machine learning has long since become a keystone technology, accelerating science and
applications in a broad range of domains. Consequently, the notion of applying learning …

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

We observe that pre-trained large language models (LLMs) are capable of autoregressively
completing complex token sequences--from arbitrary ones procedurally generated by …