Add link to paper and abstract to model card

README.md

@@ -2,14 +2,15 @@
 language:
 - vi
 library_name: transformers
+license: mit
+pipeline_tag: question-answering
 tags:
 - SemViQA
 - question-answering
 - fact-checking
 - information-retrieval
-pipeline_tag: question-answering
-license: mit
 ---
+
 ## Model Description
 - **Developed by:** [SemViQA Research Team](https://huggingface.co/SemViQA)  
 - **Fine-tuned model:** [InfoXLM](https://huggingface.co/microsoft/infoxlm-large)
@@ -17,7 +18,11 @@ license: mit
 - **Task:** Extractive QA, Evidence Extraction  
 - **Dataset:** [ISE-DSC01](https://codalab.lisn.upsaclay.fr/competitions/15497)
 
-This model is fine-tuned on [InfoXLM](https://huggingface.co/microsoft/infoxlm-large) to evaluate its performance in comparison to our proposed approaches for Vietnamese fact-checking tasks.  
+This model is fine-tuned on [InfoXLM](https://huggingface.co/microsoft/infoxlm-large) to evaluate its performance in comparison to our proposed approaches for Vietnamese fact-checking tasks. It is based on the paper [SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking](https://hf.co/papers/2503.00955).
+
+**Abstract:**
+
+
 
 ## Using pre-trained model