Update README.md

README.md

@@ -110,7 +110,7 @@ print("content:", content)
 
 ## Evaluation
 
-- Shows superior reasoning efficiency, shorter reasoning steps, higher readability, and better explanation quality compared to models of similar scale when evaluated on HRM-8K.
+- Shows superior reasoning efficiency, shorter reasoning steps, higher readability in Korean, and better explanation quality compared to models of similar scale when evaluated on HRM-8K.
 | Task       | Score | Think Step Length  | Korean Response Ratio |
 |------------|:-----:|:------------------:|:---------------------:|
 | GSM8k      |   91.9     |   896      |    94.47    |
@@ -130,10 +130,9 @@ print("content:", content)
 ## Citation
 
 ```
-@misc{KULLM-R2024,
+@misc{KULLM-R2025,
   title   = {KULLM-R: Korea University Large Language Model for Reasoning},
-  author  = {Korea University NLP Lab},
-  year    = {2024},
-  url     = {https://github.com/kullm-project/KULLM-R}
+  author  = {Korea University NLP&AI Lab},
+  year    = {2025},
 }
 ```