Newest papers

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

Priyanka, Renaud Delbru, Souhail Bakkali, Mickaël Coustaty, Antoine Doucet · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31529 · open-access PDF

Indonesian

Pengetahuan graf-to-tekst (KG-to-tekst) generasi verbalizes satu set graf pengetahuan triple ke dalam bahasa alami yang lancar. Sementara model fin-tuned encoder-decoder telah lama menjadi pendekatan standar, LLM terbaru menjadi semakin kompetitif. Kami membandingkan LLM baru-baru ini terhadap model fin-tuned encoder-decoder, menggunakan metrik berbasis referensi dan evaluasi berbasis LLM berbasis referensi bebas berbasis grafik validasi terhadap anotasi manusia. Kami melihat bahwa LLM baru-baru ini secara substansial sempit, dan dalam beberapa pengaturan menutup, kesenjangan dengan model fin-tuned pada metrik berbasis referensi, sementara melakukan b

Machine translation (Meta M2M100); the English original follows.

Abstract

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 b

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange