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

Source: [Enhancing Next-Generation Language Models with Knowledge Graphs: Extending Claude, Mistral IA, and GPT-4 via KG-BERT](<https://www.sota2.com/research/paper/693ba1676cfd488761a5504a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-13T05:01:27.798Z

Authors: Nour El Houda Ben Chaabene, Hamza Hammami

Published: 2025-12-11T09:02:45.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Text Generation on Text Generation](<https://www.sota2.com/research/sota/text-generation-on-text-generation.md>): Text Generation; Text Generation; PPL: 18.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.10440>)

[PDF](<https://arxiv.org/pdf/2512.10440.pdf>)