MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation

Understand

Prompting large language models has enabled significant recent progress in multi-step reasoning over text.

• However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low semantic coverage, hallucination, and logical inconsistency.
• We propose MURMUR, a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning.
• MURMUR is a best-first search method that generates reasoning paths using: (1) neural and symbolic modules with specific linguistic and logical skills, (2) a grammar whose production rules define valid compositions of modules, and (3) value functions that assess the quality of each reasoning step.