Enhancing Next-Generation Language Models with Knowledge Graphs: Extending Claude, Mistral IA, and GPT-4 via KG-BERT

Nour El Houda Ben Chaabene, Hamza Hammami
12/11/2025
cs.CL

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT

90% match2024

Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data

88% match2024

Enhancing Large Language Models with Reliable Knowledge Graphs

88% match2025

Injecting Knowledge Graphs into Large Language Models

87% match2025

From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies

87% match2025

KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs

87% match2025

Cite this paper

@article{chaabene2025enhancing,
  title  = {Enhancing Next-Generation Language Models with Knowledge Graphs: Extending Claude, Mistral IA, and GPT-4 via KG-BERT},
  author = {Nour El Houda Ben Chaabene and Hamza Hammami},
  year   = {2025},
  eprint = {2512.10440},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.10440v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.10440.svg)](https://codeofpaper.com/paper/2512.10440)

Discussion