English

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

Computation and Language 2025-03-03 v1 Artificial Intelligence

Abstract

We introduce a simple approach that uses a large language model (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 language model 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

Keywords

Cite

@article{arxiv.2502.20609,
  title  = {Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems},
  author = {Jędrzej Warczyński and Mateusz Lango and Ondrej Dusek},
  journal= {arXiv preprint arXiv:2502.20609},
  year   = {2025}
}
R2 v1 2026-06-28T22:01:00.658Z