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

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

In tasks like semantic parsing, instruction following, and question answering, standard deep
networks fail to generalize compositionally from small datasets. Many existing approaches …

Compositional generalization--understanding unseen combinations of seen primitives--is an
essential reasoning capability in human intelligence. The AI community mainly studies this …

Neural models greatly outperform grammar-based models across many tasks in modern
computational linguistics. This raises the question of whether linguistic principles, such as …

Human linguistic capacity is often characterized by compositionality and the generalization it
enables--human learners can produce and comprehend novel complex expressions by …

Humans possess a remarkable ability to assign novel interpretations to linguistic
expressions, enabling them to learn new words and understand community-specific …

The goal of compositional generalization benchmarks is to evaluate how well models
generalize to new complex linguistic expressions. Existing benchmarks often focus on …

Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks,
including ones that require predicting linguistic structure. However, recent work on …

We show how the AM parser, a compositional semantic parser (Groschwitz et al., 2018) can
solve compositional generalization on the COGS dataset. It is the first semantic parser that …