LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511611" target="_blank" >RIV/00216208:11320/25:10511611 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2025.emnlp-industry.142/" target="_blank" >https://aclanthology.org/2025.emnlp-industry.142/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
Original language description
We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is “trained” through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based Python code for a generator for the given domain, based on RDF triples only, with no in-domain human reference texts. The resulting system is fully interpretable, requires no supervised training data, and generates text nearly instantaneously using only a single CPU. Our experiments on the WebNLG and OpenDialKG data show that outputs produced by our approach reduce hallucination, with only slight fluency penalties compared to finetuned or prompted language models.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
R - Projekt Ramcoveho programu EK
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
ISBN
979-8-89176-333-3
ISSN
—
e-ISSN
—
Number of pages
16
Pages from-to
2025-2040
Publisher name
Association for Computational Linguistics
Place of publication
Kerrville, TX, USA
Event location
Suzhou, China
Event date
Nov 4, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—