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

Chain-of-thought prompting has demonstrated remarkable performance on various natural
language reasoning tasks. However, it tends to perform poorly on tasks which requires …

Humans can reason compositionally when presented with new tasks. Previous research
shows that appropriate prompting techniques enable large language models (LLMs) to …

Transformers have impressive generalization capabilities on tasks with a fixed context
length. However, they fail to generalize to sequences of arbitrary length, even for seemingly …

A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general
understanding of the world. Such an agent would require the ability to continually …

Sequence-to-sequence models excel at handling natural language variation, but have been
shown to struggle with out-of-distribution compositional generalization. This has motivated …

Recently, many datasets have been proposed to test the systematic generalization ability of
neural networks. The companion baseline Transformers, typically trained with default hyper …

Generic unstructured neural networks have been shown to struggle on out-of-distribution
compositional generalization. Compositional data augmentation via example recombination …

Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing,
recent work has shown that they fail in compositional generalization, ie, the ability to …

Several studies have reported the inability of Transformer models to generalize
compositionally, a key type of generalization in many NLP tasks such as semantic parsing …