Metraipolis › archive › dc_f95cb33e83a8

An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks — arXiv:2610.31529

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31529
License (as archived)
CC0-1.0
Archived
2026-10-23T15:21:12.098Z
SHA-256 of the archived text
1ebde7d1a1b23dbd7f2a69d803ab9ae5afa45c566780201d3875565eaf9f4a46
Stable URL of this page
https://metraipolis.com/documento/dc_f95cb33e83a8

How to cite

An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks — arXiv:2610.31529 — arXiv (en), https://arxiv.org/abs/2610.31529 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f95cb33e83a8 (Metraipolis archive dc_f95cb33e83a8, sha256 1ebde7d1a1b23dbd7f2a69d803ab9ae5afa45c566780201d3875565eaf9f4a46)
BibTeX
@misc{dcf95cb33e83a8,
  title = {An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks — arXiv:2610.31529},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31529},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f95cb33e83a8; sha256 1ebde7d1a1b23dbd7f2a69d803ab9ae5afa45c566780201d3875565eaf9f4a46},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31529. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge graph-to-text (KG-to-text) generation verbalizes a set of knowledge graph triples into fluent natural language. While fine-tuned encoder-decoder models have long been the standard approach, recent LLMs are becoming increasingly competitive. We benchmark recent LLMs against fine-tuned encoder-decoder models, using reference-based metrics and graph-grounded reference-free LLM-based evaluation validated against human annotations. We observed that recent LLMs substantially narrow, and in several settings close, the gap with fine-tuned models on reference-based metrics, while performing better on graph-grounded metrics. LLM-based evaluation scores show limited correlation with reference-based metrics, suggesting that the two approaches capture different aspects of generation quality. Graph-grounded evaluation reveals that prompted models produce fewer contradictions and triple omissions than fine-tuned models, and these errors increase more rapidly with graph size for fine-tuned models, highlighting differences between the two approaches that reference-based metrics may not fully capture.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.31529 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-23T15:09:38.368Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).