TITLE = """<h1 align="center" id="space-title"> KG LLM Leaderboard</h1>"""

INTRODUCTION_TEXT = f"""
🐨 KG LLM Leaderboard aims to track, rank, and evaluate the performance of released Large Language Models on traditional KBQA/KGQA datasets.

The data on this page is sourced from a research paper. If you intend to use the data from this page, please remember to cite the following source: https://arxiv.org/abs/2303.07992

We compare the current SOTA traditional KBQA models (fine-tuned (FT) and zero-shot (ZS)),

LLMs in the GPT family, and Other Non-GPT LLM. In QALD-9 and LC-quad2, the evaluation metric used is F1, while other datasets use Accuracy (Exact match).

"""

LLM_BENCHMARKS_TEXT = f"""
ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge. 

Therefore, there is growing interest in exploring whether ChatGPT can replace traditional knowledge-based question answering (KBQA) models.

Although there have been some works analyzing the question answering performance of ChatGPT, there is still a lack of large-scale, comprehensive testing of various types of complex questions to analyze the limitations of the model.

In this paper, we present a framework that follows the black-box testing specifications of CheckList proposed by Microsoft. 

We evaluate ChatGPT and its family of LLMs on eight real-world KB-based complex question answering datasets, which include six English datasets and two multilingual datasets.

The total number of test cases is approximately 190,000.

"""



CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@article{tan2023evaluation,
    title={Evaluation of ChatGPT as a question answering system for answering complex questions},
    author={Tan, Yiming and Min, Dehai and Li, Yu and Li, Wenbo and Hu, Nan and Chen, Yongrui and Qi, Guilin},
    journal={arXiv preprint arXiv:2303.07992},
    year={2023}
}
"""