Update README.md

README.md

@@ -62,7 +62,7 @@ print(out[0]["generated_text"])
 
 ---
 
-## 📊 Results (Merged Benchmark Summary)
+## 📊 Results
 
 *Hala models are placed at the end of each size category; best **Average** per category is in bold.*
 
@@ -99,7 +99,7 @@ print(out[0]["generated_text"])
 | 7B–9B | QCRI/Fanar-1-9B-Instruct                    |     9B |    76.4 |       65.8 |  52.7 |      73.3 |     88.3 |       58.6 |     69.2 |
 | 7B–9B | **Hala‑9B**                                 |     9B |    78.3 |       65.6 |  53.8 |      70.4 |     89.6 |       61.4 | **69.9** |
 
-> **Evaluation protocol**: `lighteval` on **ArabicMMLU (OALL‑2)**.
+> **Evaluation protocol**: `lighteval` on **ArabicMMLU (OALL‑2)** excluding AlRage.
 
 ---
 
@@ -108,11 +108,10 @@ print(out[0]["generated_text"])
 If you find **Hala** useful, please cite:
 
 ```bibtex
-@article{hala2025technicalreport,
-  title   = {Hala Technical Report: Building Arabic-Centric Instruction \& Translation Models at Scale},
-  author  = {Hammoud, Hasan Abed Al Kader and Zbeeb, Mohammad and Ghanem, Bernard},
-  journal = {arXiv preprint},
-  year    = {2025},
-  note    = {KAUST},
+@misc{hammoud2025halatechnicalreportbuilding,
+      title={Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale}, 
+      author={Hasan Abed Al Kader Hammoud and Mohammad Zbeeb and Bernard Ghanem},
+      year={2025},
+      url={https://arxiv.org/abs/2509.14008}, 
 }
 ```