Enhance model card with primary paper link

README.md

@@ -1,19 +1,19 @@
 ---
 base_model: LGAI-EXAONE/EXAONE-4.0-1.2B
-base_model_relation: quantized
-license: other
-license_name: exaone
-license_link: LICENSE
 language:
 - en
 - ko
 - es
+library_name: transformers
+license: other
+license_name: exaone
+license_link: LICENSE
+pipeline_tag: text-generation
 tags:
 - lg-ai
 - exaone
 - exaone-4.0
-pipeline_tag: text-generation
-library_name: transformers
+base_model_relation: quantized
 ---
 
 <p align="center">
@@ -24,6 +24,8 @@ library_name: transformers
 
 # EXAONE-4.0-1.2B-FP8
 
+The model was presented in the paper [EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes](https://huggingface.co/papers/2507.11407).
+
 ## Introduction
 
 We introduce **EXAONE 4.0**, which integrates a **Non-reasoning mode** and **Reasoning mode** to achieve both the excellent usability of [EXAONE 3.5](https://github.com/LG-AI-EXAONE/EXAONE-3.5) and the advanced reasoning abilities of [EXAONE Deep](https://github.com/LG-AI-EXAONE/EXAONE-Deep). To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended
@@ -1142,4 +1144,4 @@ The model is licensed under [EXAONE AI Model License Agreement 1.2 - NC](./LICEN
 
 ## Contact
 
-LG AI Research Technical Support: [email protected]
+LG AI Research Technical Support: [email protected]