EXAONE 4.5 Technical Report

2026-04-09

AI Summary

This work addresses the limitations of existing open-source vision-language models in industrial document understanding and Korean-language scenarios. We propose the first LG AI open-source vision-language model, built upon the EXAONE 4.0 framework and featuring a dedicated vision encoder to enable native multimodal pretraining. The model leverages a large-scale, high-quality, document-centric corpus and supports ultra-long context modeling with a 256K-token window. It demonstrates competitive performance on general multimodal benchmarks and significantly outperforms state-of-the-art models of comparable scale in both document understanding and Korean-context reasoning tasks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Large Vision Models
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, enabling native multimodal pretraining over both visual and textual modalities. The model is trained on large-scale data with careful curation, particularly emphasizing document-centric corpora that align with LG's strategic application domains. This targeted data design enables substantial performance gains in document understanding and related tasks, while also delivering broad improvements across general language capabilities. EXAONE 4.5 extends context length up to 256K tokens, facilitating long-context reasoning and enterprise-scale use cases. Comparative evaluations demonstrate that EXAONE 4.5 achieves competitive performance in general benchmarks while outperforming state-of-the-art models of similar scale in document understanding and Korean contextual reasoning. As part of LG's ongoing effort toward practical industrial deployment, EXAONE 4.5 is designed to be continuously extended with additional domains and application scenarios to advance AI for a better life.

Problem

• vision language model
• document understanding
• long-context reasoning
• Korean contextual reasoning
• multimodal pretraining

Innovation

• vision-language model
• multimodal pretraining
• document understanding
• long-context reasoning
• open-weight