NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization

TL;DR

NeSyCoCo is a neuro-symbolic framework that enhances compositional generalization in vision-language reasoning by integrating large language models with differentiable neural modules, addressing key limitations of prior approaches.

Contribution

It introduces a novel neuro-symbolic approach that uses LLMs for symbolic representation generation and differentiable composition, improving adaptability and generalization.

Findings

Achieves state-of-the-art on ReaSCAN and CLEVR-CoGenT benchmarks.

Demonstrates robust performance with novel concepts in CLEVR-SYN.

Addresses key challenges in neuro-symbolic reasoning with innovative techniques.

Abstract

Compositional generalization is crucial for artificial intelligence agents to solve complex vision-language reasoning tasks. Neuro-symbolic approaches have demonstrated promise in capturing compositional structures, but they face critical challenges: (a) reliance on predefined predicates for symbolic representations that limit adaptability, (b) difficulty in extracting predicates from raw data, and (c) using non-differentiable operations for combining primitive concepts. To address these issues, we propose NeSyCoCo, a neuro-symbolic framework that leverages large language models (LLMs) to generate symbolic representations and map them to differentiable neural computations. NeSyCoCo introduces three innovations: (a) augmenting natural language inputs with dependency structures to enhance the alignment with symbolic representations, (b) employing distributed word representations to link diverse, linguistically motivated logical predicates to neural modules, and (c) using the soft composition of normalized predicate scores to align symbolic and differentiable reasoning. Our framework achieves state-of-the-art results on the ReaSCAN and CLEVR-CoGenT compositional generalization benchmarks and demonstrates robust performance with novel concepts in the CLEVR-SYN benchmark.