Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems

Abstract: We introduce a simple approach that uses a LLM to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental evaluation on the WebNLG dataset showed that such a constructed system produces text of better quality (according to the BLEU and BLEURT metrics) than the same LLM prompted to directly produce outputs, and produces fewer hallucinations than a BART LLM fine-tuned on the same data. Furthermore, at runtime, the approach generates text in a fraction of the processing time required by neural approaches, using only a single CPU