LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909972447625216 |
|---|---|
| author | Lango, Mateusz Dušek, Ondřej |
| author_facet | Lango, Mateusz Dušek, Ondřej |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18360 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators Lango, Mateusz Dušek, Ondřej Computation and Language Artificial Intelligence 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 |
| title | LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.18360 |