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("anli_r1", "acc", "ANLI")
    # task1 = Task("logiqa", "acc_norm", "LogiQA")

    # retrieval tasks
    mrr = Task("retrieval", "mrr", "MRR ⬆️")
    map = Task("retrieval", "map", "MAP ⬆️")

    # generation tasks
    em = Task("generation", "em", "EM ⬆️")
    f1 = Task("generation", "f1", "F1 ⬆️")
    rouge1 = Task("generation", "rouge1", "Rouge-1 ⬆️")
    rouge2 = Task("generation", "rouge2", "Rouge-2 ⬆️")
    rougeL = Task("generation", "rougeL", "Rouge-L ⬆️")

    accuracy = Task("generation", "accuracy", "ACC ⬆️")
    completeness = Task("generation", "completeness", "COMP ⬆️")
    hallucination = Task("generation", "hallucination", "HAL ⬇️")
    utilization = Task("generation", "utilization", "UTIL ⬆️")
    numerical_accuracy = Task("generation", "numerical_accuracy", "MACC ⬆️")


NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------



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

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
<div align="center">
Please contact us if you would like to submit your model to this leaderboard. Email: wangshuting@ruc.edu.cn
如果您想将您的模型提交到此排行榜，请联系我们。邮箱：wangshuting@ruc.edu.cn
</div>
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = """
# Leaderboard Information

We introduce an omnidirectional and automatic RAG benchmark, **OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain**, in the financial domain. Our benchmark is characterized by its multi-dimensional evaluation framework, including:

1. a matrix-based RAG scenario evaluation system that categorizes queries into five task classes and 16 financial topics, leading to a structured assessment of diverse query scenarios;
2. a multi-dimensional evaluation data generation approach, which combines GPT-4-based automatic generation and human annotation, achieving an 87.47% acceptance ratio in human evaluations on generated instances;
3. a multi-stage evaluation system that evaluates both retrieval and generation performance, result in a comprehensive evaluation on the RAG pipeline;
4. robust evaluation metrics derived from rule-based and LLM-based ones, enhancing the reliability of assessments through manual annotations and supervised fine-tuning of an LLM evaluator.

Useful Links: 📝 [Paper](https://arxiv.org/abs/2412.13018) • 🤗 [Hugging Face](https://huggingface.co/collections/RUC-NLPIR/omnieval-67629ccbadd3a715a080fd25) • 🧩 [Github](https://github.com/RUC-NLPIR/OmniEval)

We have trained two models from Qwen2.5-7B by the lora strategy and human-annotation labels to implement model-based evaluation.Note that the evaluator of hallucination is different from other four.

We provide the evaluator for other metrics except hallucination in this repo.

# 🌟 Citation
"""

EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model

### 1) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.

Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!

### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!

### 3) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗

### 4) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card

## In case of model failure
If your model is displayed in the `FAILED` category, its execution stopped.
Make sure you have followed the above steps first.
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@misc{wang2024omnievalomnidirectionalautomaticrag,
      title={OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain}, 
      author={Shuting Wang and Jiejun Tan and Zhicheng Dou and Ji-Rong Wen},
      year={2024},
      eprint={2412.13018},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.13018}, 
}
"""