src/about.py

from dataclasses import dataclass
from enum import Enum

@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


# Select your tasks here
# ---------------------------------------------------
class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    task0 = Task("Math", "acc", "Math")
    task1 = Task("Chemistry", "acc", "Chemistry")
    task2 = Task("Physics", "acc", "Physics")
    task3 = Task("Arabic", "acc", "Arabic")
    task4 = Task("English", "acc", "English")
    task5 = Task("Religion", "acc", "Religion")
    task6 = Task("Persian Literature", "acc", "Persian Literature")
NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">IRUEX leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Intro text
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works

## Reproducibility
To reproduce our results, here is the commands you can run:

"""

# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">IRUEX Leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
**Welcome to the IRUEX Leaderboard!**  
This platform evaluates large language models based on Iran's University Entrance Exam subjects.  
[Explore the IRUEX Dataset](https://github.com/hamedkhaledi/IRUEX-dataset) on GitHub.
"""

# Which evaluations are you running? How can people reproduce them?
LLM_BENCHMARKS_TEXT = """
## Evaluation Process

We assess models across various subjects, including Math, Chemistry, Physics, Arabic, English, Religion, and Persian Literature. Each model's performance is measured using accuracy metrics specific to each subject.

## Reproducibility

To reproduce our results, execute the following commands:

```bash
# Example command to run evaluations
python evaluate_model.py --model_name your_model_name --task Math --num_fewshot 0
```
"""

EVALUATION_QUEUE_TEXT = ""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@inproceedings{khademi-khaledi-faili-2025-iruex,
    title = "{IRUEX}: A Study on Large Language Models' Problem-Solving Skills in Iran's University Entrance Exam",
    author = "Khademi Khaledi, Hamed and Faili, Heshaam",
    editor = "Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Di Eugenio, Barbara and Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-main.434/",
    pages = "6505--6519",
}
"""