Update Technical Report

README.md

@@ -36,7 +36,7 @@ In the EXAONE 4.0 architecture, we apply new architectural changes compared to p
 1. **Hybrid Attention**: For the 32B model, we adopt hybrid attention scheme, which combines *Local attention (sliding window attention)* with *Global attention (full attention)* in a 3:1 ratio. We do not use RoPE (Rotary Positional Embedding) for global attention for better global context understanding.
 2. **QK-Reorder-Norm**: We adopt the Post-LN (LayerNorm) scheme for transformer blocks instead of Pre-LN, and we add RMS normalization right after the Q and K projection. It helps yield better performance on downstream tasks despite consuming more computation.
 
-For more details, please refer to our [technical report](https://www.lgresearch.ai/data/cdn/upload/EXAONE_4_0.pdf), [blog](https://www.lgresearch.ai/blog/view?seq=576), and [GitHub](https://github.com/LG-AI-EXAONE/EXAONE-4.0).
+For more details, please refer to our [technical report](https://arxiv.org/abs/2507.11407), [blog](https://www.lgresearch.ai/blog/view?seq=576), and [GitHub](https://github.com/LG-AI-EXAONE/EXAONE-4.0).
 
 
 ### Model Configuration
@@ -140,7 +140,7 @@ git clone --single-branch -b add-exaone4 https://github.com/lgai-exaone/llama.cp
 
 ## Performance
 
-The following tables show the evaluation results of each model, with reasoning and non-reasoning mode. The evaluation details can be found in the [technical report](https://www.lgresearch.ai/data/cdn/upload/EXAONE_4_0.pdf).
+The following tables show the evaluation results of each model, with reasoning and non-reasoning mode. The evaluation details can be found in the [technical report](https://arxiv.org/abs/2507.11407).
 
 - ✅ denotes the model has a hybrid reasoning capability, evaluated by selecting reasoning / non-reasoning on the purpose.
 - To assess Korean **practical** and **professional** knowledge, we adopt both the [KMMLU-Redux](https://huggingface.co/datasets/LGAI-EXAONE/KMMLU-Redux) and [KMMLU-Pro](https://huggingface.co/datasets/LGAI-EXAONE/KMMLU-Pro) benchmarks. Both datasets are publicly released!
@@ -1089,7 +1089,14 @@ The model is licensed under [EXAONE AI Model License Agreement 1.2 - NC](./LICEN
 
 ## Citation
 
-TBD
+```
+@article{exaone-4.0,
+  title={EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes},
+  author={{LG AI Research}},
+  journal={arXiv preprint arXiv:2507.11407},
+  year={2025}
+}
+```
 
 
 ## Contact