Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910850007171072 |
|---|---|
| author | Warczyński, Jędrzej Lango, Mateusz Dusek, Ondrej |
| author_facet | Warczyński, Jędrzej Lango, Mateusz Dusek, Ondrej |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems Warczyński, Jędrzej Lango, Mateusz Dusek, Ondrej Computation and Language Artificial Intelligence 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 |
| title | Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.20609 |