Spaces:
Running
Running
Update src/streamlit_app.py
Browse files- src/streamlit_app.py +13 -12
src/streamlit_app.py
CHANGED
|
@@ -190,18 +190,19 @@ Letβs build better evaluations for expert-level AI β together ππ€
|
|
| 190 |
"""
|
| 191 |
)
|
| 192 |
|
| 193 |
-
st.markdown(## π Citation)
|
| 194 |
-
st.write(
|
| 195 |
-
"""
|
| 196 |
-
```bibtex
|
| 197 |
-
@article{ruan2025expertlongbench,
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
}
|
| 203 |
-
"""
|
| 204 |
-
)
|
|
|
|
| 205 |
# # βββ Tabs ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 206 |
# tab1, tab2, tab3, tab4 = st.tabs(["π Leaderboard", "π Benchmark Details", "π€ Submit Your Model", "π§© Community Contributions Welcome"])
|
| 207 |
|
|
|
|
| 190 |
"""
|
| 191 |
)
|
| 192 |
|
| 193 |
+
# st.markdown(## π Citation)
|
| 194 |
+
# st.write(
|
| 195 |
+
# """
|
| 196 |
+
# ```bibtex
|
| 197 |
+
# @article{ruan2025expertlongbench,
|
| 198 |
+
# title={ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists},
|
| 199 |
+
# author={Ruan, Jie and Nair, Inderjeet and Cao, Shuyang and Liu, Amy and Munir, Sheza and Pollens-Dempsey, Micah and Chiang, Tiffany and Kates, Lucy and David, Nicholas and Chen, Sihan and others},
|
| 200 |
+
# journal={arXiv preprint arXiv:2506.01241},
|
| 201 |
+
# year={2025}
|
| 202 |
+
# }
|
| 203 |
+
# """
|
| 204 |
+
# )
|
| 205 |
+
|
| 206 |
# # βββ Tabs ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 207 |
# tab1, tab2, tab3, tab4 = st.tabs(["π Leaderboard", "π Benchmark Details", "π€ Submit Your Model", "π§© Community Contributions Welcome"])
|
| 208 |
|