Saved in:
Bibliographic Details
Main Authors: Chaabene, Nour El Houda Ben, Hammami, Hamza
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10440
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914194324979712
author Chaabene, Nour El Houda Ben
Hammami, Hamza
author_facet Chaabene, Nour El Houda Ben
Hammami, Hamza
contents Large language models (LLMs) like Claude, Mistral IA, and GPT-4 excel in NLP but lack structured knowledge, leading to factual inconsistencies. We address this by integrating Knowledge Graphs (KGs) via KG-BERT to enhance grounding and reasoning. Experiments show significant gains in knowledge-intensive tasks such as question answering and entity linking. This approach improves factual reliability and enables more context-aware next-generation LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10440
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Next-Generation Language Models with Knowledge Graphs: Extending Claude, Mistral IA, and GPT-4 via KG-BERT
Chaabene, Nour El Houda Ben
Hammami, Hamza
Computation and Language
Large language models (LLMs) like Claude, Mistral IA, and GPT-4 excel in NLP but lack structured knowledge, leading to factual inconsistencies. We address this by integrating Knowledge Graphs (KGs) via KG-BERT to enhance grounding and reasoning. Experiments show significant gains in knowledge-intensive tasks such as question answering and entity linking. This approach improves factual reliability and enables more context-aware next-generation LLMs.
title Enhancing Next-Generation Language Models with Knowledge Graphs: Extending Claude, Mistral IA, and GPT-4 via KG-BERT
topic Computation and Language
url https://arxiv.org/abs/2512.10440