update about section

README.md

@@ -16,7 +16,7 @@ space_ci:
     - HF_TOKEN
 tags:
   - leaderboard
-short_description: Track, rank and evaluate open Arabic LLMs and chatbots
+short_description: Track, rank and evaluate Open Telecom LLMs and chatbots
 ---
 
 # Start the configuration

src/about.py

@@ -11,12 +11,9 @@ class Task:
 # ---------------------------------------------------
 class Tasks(Enum):
     # # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    tsg_avg = Task("custom|3gpp:tsg|0", "em", "TSG-AVG")
+    tsg_avg = Task("custom|3gpp:tsg|0", "em", "3GPP-TSG")
     tele_EQ = Task("custom|telecom:math|0", "em", "TELE-EQ")
-    # tsg_sa = Task("3gpp|tsg_sa:_average|0", "acc", "TSG-SA")
-    # tsg_ct = Task("3gpp|tsg_ct:_average|0", "acc", "TSG-CT")
-    # tele_EQ = Task("tii|tele_EQ:_average|0", "cosine_similarity", "TELE-EQ")
-    # tele_QnA = Task("huawei|tele_QnA:_average|0", "acc", "TELE-QnA")
+    tele_QnA = Task("custom|telecom:qna|0", "em", "TELE-QnA")
 
     
 NUM_FEWSHOT = 0 # Change with your few shot
@@ -32,14 +29,14 @@ BOTTOM_LOGO = """<img src="https://avatars.githubusercontent.com/u/148767883?v=4
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-🌐 The Open TELCOM LLM Leaderboard : Evaluate and compare the performance of Telecom Large Language Models (LLMs).
+🌐 The Open Telecom LLM Leaderboard : Evaluate and compare the performance of Telecom Large Language Models (LLMs).
 
 
 When you submit a model on the "Submit here!" page, it is automatically evaluated on a set of benchmarks. 
 
 The GPU used for evaluation is operated with the support of  __[Huawei Technologies France](https://www.huawei.com/)__, __[Technology Innovation Institute (TII)](https://www.tii.ae/)__, and  __[GSM Association (GSMA)](https://www.gsma.com/)__.
 
-The datasets used for evaluation consist of datasets that are the `TeleQna` benchmark from [TeleQna](https://github.com/netop-team/TeleQnA) and `BENCHMARK` benchmark from [BENCHMARK_HUB](https://benchmarkwebsite.com) to assess reasoning, language understanding, commonsense, and more. 
+The datasets used for evaluation are the `TeleQnA` benchmark from [TeleQnA](https://github.com/netop-team/TeleQnA), `TeleEQ` benchmark from [TeleEQ](https://arxiv.org/pdf/2407.09424), and `3GPP-TSG` benchmark from [3GPP-TSG](https://arxiv.org/pdf/2407.09424) to assess reasoning, language understanding, commonsense, and more. 
 
 More details about the benchmarks and the evaluation process is provided on the “About” page.
 """
@@ -129,12 +126,12 @@ If everything is done, check you can launch the LightEval script on your model l
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 CITATION_BUTTON_TEXT = r"""
-@misc{Netop,
-  author = {xxxx, },
-  title = {Open Telco LLM Leaderboard},
+@misc{otellm,
+  author = {Sana, Mohamed and De Domenico, Antonio and Debbah, Merouane and Zhao, Qiyang},
+  title = {Open Telecom LLM Leaderboard},
   year = {2024},
-  publisher = {Netop},
-  howpublished = "\url{https://huggingface.co/spaces/netop/Open-Telecom-LLM-Leaderboard}"
+  publisher = {otellm},
+  howpublished = "\url{https://huggingface.co/spaces/otellm/Open-Telecom-LLM-Leaderboard}"
 }
 
 @article{maatouk2023teleqna,