Spaces:
Running
Running
Commit
Β·
a38d810
1
Parent(s):
6ed5ca9
Update icon
Browse files- __pycache__/utils.cpython-39.pyc +0 -0
- app.py +1 -0
- utils.py +2 -2
__pycache__/utils.cpython-39.pyc
ADDED
|
Binary file (3.21 kB). View file
|
|
|
app.py
CHANGED
|
@@ -18,6 +18,7 @@ with block:
|
|
| 18 |
value=CITATION_BUTTON_TEXT,
|
| 19 |
label=CITATION_BUTTON_LABEL,
|
| 20 |
elem_id="citation-button",
|
|
|
|
| 21 |
)
|
| 22 |
gr.Markdown(
|
| 23 |
TABLE_INTRODUCTION
|
|
|
|
| 18 |
value=CITATION_BUTTON_TEXT,
|
| 19 |
label=CITATION_BUTTON_LABEL,
|
| 20 |
elem_id="citation-button",
|
| 21 |
+
lines=6,
|
| 22 |
)
|
| 23 |
gr.Markdown(
|
| 24 |
TABLE_INTRODUCTION
|
utils.py
CHANGED
|
@@ -24,8 +24,8 @@ LEADERBORAD_INTRODUCTION = """# TheoremQA Leaderboard
|
|
| 24 |
π Welcome to the leaderboard of the **TheoremQA**! π¦ *A Theorem-driven Question Answering dataset* (**EMNLP 2023**)
|
| 25 |
<div style="display: flex; flex-wrap: wrap; align-items: center; gap: 10px;">
|
| 26 |
<a href='https://arxiv.org/abs/2305.12524'><img src='https://img.shields.io/badge/cs.CV-Paper-b31b1b?logo=arxiv&logoColor=red'></a>
|
| 27 |
-
<a href='https://github.com/TIGER-AI-Lab/TheoremQA'><img src='https://img.shields.io/badge/
|
| 28 |
-
<a href
|
| 29 |
</div>
|
| 30 |
|
| 31 |
We propose the first question-answering dataset driven by STEM theorems. We annotated 800 QA pairs covering 350+ theorems spanning across Math, EE&CS, Physics and Finance. The dataset is collected by human experts with very high quality. We provide the dataset as a new benchmark to test the limit of large language models to apply theorems to solve challenging university-level questions.
|
|
|
|
| 24 |
π Welcome to the leaderboard of the **TheoremQA**! π¦ *A Theorem-driven Question Answering dataset* (**EMNLP 2023**)
|
| 25 |
<div style="display: flex; flex-wrap: wrap; align-items: center; gap: 10px;">
|
| 26 |
<a href='https://arxiv.org/abs/2305.12524'><img src='https://img.shields.io/badge/cs.CV-Paper-b31b1b?logo=arxiv&logoColor=red'></a>
|
| 27 |
+
<a href='https://github.com/TIGER-AI-Lab/TheoremQA'><img src='https://img.shields.io/badge/Github-Repo-grey?logo=github&logoColor=white'></a>
|
| 28 |
+
<a href='https://hits.seeyoufarm.com'><img src='https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fhuggingface.co%2Fspaces%2FTIGER-Lab%2FTheoremQA-Leaderboard&count_bg=%23C7C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false'></a>
|
| 29 |
</div>
|
| 30 |
|
| 31 |
We propose the first question-answering dataset driven by STEM theorems. We annotated 800 QA pairs covering 350+ theorems spanning across Math, EE&CS, Physics and Finance. The dataset is collected by human experts with very high quality. We provide the dataset as a new benchmark to test the limit of large language models to apply theorems to solve challenging university-level questions.
|