Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning
arXiv:2107.02794
Abstract
Human reasoning can often be understood as an interplay between two systems: the intuitive and associative ("System 1") and the deliberative and logical ("System 2"). Neural sequence models -- which have been increasingly successful at performing complex, structured tasks -- exhibit the advantages and failure modes of System 1: they are fast and learn patterns from data, but are often inconsistent and incoherent. In this work, we seek a lightweight, training-free means of improving existing System 1-like sequence models by adding System 2-inspired logical reasoning. We explore several variations on this theme in which candidate generations from a neural sequence model are examined for logical consistency by a symbolic reasoning module, which can either accept or reject the generations. Our approach uses neural inference to mediate between the neural System 1 and the logical System 2. Results in robust story generation and grounded instruction-following show that this approach can increase the coherence and accuracy of neurally-based generations.
arXiv commentNeurIPS 2021
References in corpus (9)
- Decoupled Weight Decay Regularization
- Language Models are Few-Shot Learners
- Zero-Shot Text-to-Image Generation
- A Benchmark for Systematic Generalization in Grounded Language Understanding
- Controlling Style in Generated Dialogue
- Learning Compositional Rules via Neural Program Synthesis
- Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data
- Think before you act: A simple baseline for compositional generalization
- Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule