tangtang
commited on
Commit
·
03ff9a5
1
Parent(s):
6be31de
Update space1
Browse files- app.py +5 -0
- src/about.py +0 -19
app.py
CHANGED
|
@@ -93,7 +93,12 @@ demo = gr.Blocks(css=custom_css)
|
|
| 93 |
with demo:
|
| 94 |
gr.HTML(TITLE)
|
| 95 |
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
|
|
|
|
| 97 |
with gr.Tabs(elem_classes="tab-buttons") as tabs:
|
| 98 |
with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
|
| 99 |
leaderboard = init_leaderboard(LEADERBOARD_DF)
|
|
|
|
| 93 |
with demo:
|
| 94 |
gr.HTML(TITLE)
|
| 95 |
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
|
| 96 |
+
def display_radar_chart():
|
| 97 |
+
return """
|
| 98 |
+
<iframe src="https://tangxuemei1995.github.io/LitReview_reusults/clean.html" style="width: 100%; height: 500px; border: none;"></iframe>
|
| 99 |
+
"""
|
| 100 |
|
| 101 |
+
gr.HTML(display_radar_chart())
|
| 102 |
with gr.Tabs(elem_classes="tab-buttons") as tabs:
|
| 103 |
with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
|
| 104 |
leaderboard = init_leaderboard(LEADERBOARD_DF)
|
src/about.py
CHANGED
|
@@ -42,25 +42,6 @@ INTRODUCTION_TEXT = """
|
|
| 42 |
This leaderboard evaluates Large Language Models (LLMs) on their ability to perform automated literature review tasks, including reference generation, abstract writing, and review composition.<br>
|
| 43 |
It is based on the study: <b>Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition.</b><br>
|
| 44 |
The leaderboard measures how well different models perform in references generation, factually consistent, and stylistically appropriate academic texts.<br><br>
|
| 45 |
-
|
| 46 |
-
<div style="display:flex; gap:20px; justify-content:space-between;">
|
| 47 |
-
<div style="text-align:center;">
|
| 48 |
-
<img src="https://huggingface.co/datasets/XuemeiTang/llm_litReview_images/resolve/main/acc_score.png?raw=true" width="200"><br>
|
| 49 |
-
Reference Generation: Precision
|
| 50 |
-
</div>
|
| 51 |
-
<div style="text-align:center;">
|
| 52 |
-
<img src="" width="200"><br>
|
| 53 |
-
Abstract Writing: True
|
| 54 |
-
</div>
|
| 55 |
-
<div style="text-align:center;">
|
| 56 |
-
<img src="https://huggingface.co/datasets/XuemeiTang/llm_litReview_images/resolve/main/acc_score_t3.png?raw=true" width="200"><br>
|
| 57 |
-
Review Composition: Precision
|
| 58 |
-
</div>
|
| 59 |
-
<div style="text-align:center;">
|
| 60 |
-
<img src="https://huggingface.co/datasets/XuemeiTang/llm_litReview_images/resolve/main/kpr_score.png?raw=true" width="200"><br>
|
| 61 |
-
Literature Review Writing: KPR
|
| 62 |
-
</div>
|
| 63 |
-
</div>
|
| 64 |
"""
|
| 65 |
|
| 66 |
|
|
|
|
| 42 |
This leaderboard evaluates Large Language Models (LLMs) on their ability to perform automated literature review tasks, including reference generation, abstract writing, and review composition.<br>
|
| 43 |
It is based on the study: <b>Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition.</b><br>
|
| 44 |
The leaderboard measures how well different models perform in references generation, factually consistent, and stylistically appropriate academic texts.<br><br>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"""
|
| 46 |
|
| 47 |
|