update readme

app.py

@@ -124,15 +124,15 @@ with demo:
 
         with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=3):
             gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
-    # with gr.Row():
-    #     with gr.Accordion("📙 Citation", open=False):
-    #         citation_button = gr.Textbox(
-    #             value=CITATION_BUTTON_TEXT,
-    #             label=CITATION_BUTTON_LABEL,
-    #             lines=20,
-    #             elem_id="citation-button",
-    #             show_copy_button=True,
-    #         )
+    with gr.Row():
+        with gr.Accordion("📙 Citation", open=False):
+            citation_button = gr.Textbox(
+                value=CITATION_BUTTON_TEXT,
+                label=CITATION_BUTTON_LABEL,
+                lines=20,
+                elem_id="citation-button",
+                show_copy_button=True,
+            )
     gr.Markdown(CONTACT_TEXT, elem_classes="markdown-text")
 
 demo.launch(share=True)

src/display/about.py

@@ -36,7 +36,7 @@ This leaderboard evaluates Large Language Models (LLMs) on Southeast Asian (SEA)
 """
 
 INTRODUCTION_TEXT = """
-This leaderboard evaluates Large Language Models (LLMs) on Southeast Asian (SEA) languages through two comprehensive benchmarks - SeaExam and SeaBench:
+This leaderboard evaluates Large Language Models (LLMs) on Southeast Asian (SEA) languages through two comprehensive benchmarks - SeaExam and SeaBench [[Paper](https://aclanthology.org/2025.findings-naacl.341/)]:
 * **SeaExam** assesses world knowledge and reasoning capabilities through exam-style questions (for both base and chat version models) [[data (public)](https://huggingface.co/datasets/SeaLLMs/SeaExam)] [[eval code](https://github.com/DAMO-NLP-SG/SeaExam)]
 * **SeaBench** evaluates instruction-following abilities and multi-turn conversational skills (thus only for chat version models). [[data (public)](https://huggingface.co/datasets/SeaLLMs/SeaBench)] [[eval code](https://github.com/DAMO-NLP-SG/SeaBench?tab=readme-ov-file)]
 
@@ -121,11 +121,22 @@ If everything is done, check you can launch the EleutherAIHarness on your model
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 CITATION_BUTTON_TEXT = r"""
+@inproceedings{liu-etal-2025-seaexam,
+    title = "{S}ea{E}xam and {S}ea{B}ench: Benchmarking {LLM}s with Local Multilingual Questions in {S}outheast {A}sia",
+    author = "Liu, Chaoqun  and Zhang, Wenxuan  and Ying, Jiahao  and Aljunied, Mahani  and Luu, Anh Tuan  and  Bing, Lidong",
+    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
+    month = apr,
+    year = "2025",
+    address = "Albuquerque, New Mexico",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.findings-naacl.341/",
+    pages = "6119--6136",
+    ISBN = "979-8-89176-195-7"
 }
 """
 
 CONTACT_TEXT = f"""
 ## Contact
 
-If you have any questions or want to include your models in the leaderboard, please contact Chaoqun Liu (<chaoqun.liu@alibaba-inc.com>) and [Wenxuan Zhang](https://isakzhang.github.io/).
+If you have any questions or want to include your models in the leaderboard, please contact [Chaoqun Liu](https://liuchaoqun.github.io/) and [Wenxuan Zhang](https://isakzhang.github.io/).
 """