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("en_prompts", "f1", "PromptsEN") task1 = Task("en_responses", "f1", "ResponsesEN") task2 = Task("de_prompts", "f1", "PromptsDE") task3 = Task("fr_prompts", "f1", "PromptsFR") task4 = Task("it_prompts", "f1", "PromptsIT") task5 = Task("es_prompts", "f1", "PromptsES") NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name TITLE = """
""" # What does your leaderboard evaluate? INTRODUCTION_TEXT = """""" # Which evaluations are you running? how can people reproduce what you have? LLM_BENCHMARKS_TEXT = f""" ## GuardBench Leaderboard Welcome to the **GuardBench's Leaderboard**, an *independent* benchmark designed to evaluate guardrail models. The leaderboard reports results for the following datasets: - **PromptsEN**: 30k+ English prompts compiled from multiple sources - **ResponsesEN**: 33k+ English single-turn conversations from multiple sources where the AI-generated response may be safe or unsafe - **PromptsDE** 30k+ German prompts - **PromptsFR**: 30k+ French prompts - **PromptsIT**: 30k+ Italian prompts - **PromptsES**: 30k+ Spanish prompts Evaluation **results** are shown in terms of **F1**. For a fine-grained evaluation, please see our publications referenced below. ## Guardrail Models Guardrail models are Large Language Models fine-tuned for safety classification, employed to detect unsafe content in human-AI interactions. By complementing other safety measures such as safety alignment, they aim to prevent generative AI systems from providing harmful information to the users. ## GuardBench GuardBench is a large-scale benchmark for guardrail models comprising *40 safety evaluation datasets* that was recently proposed to evaluate their effectiveness. You can find more information in the [paper](https://aclanthology.org/2024.emnlp-main.1022) we presented at EMNLP 2024. ## Python GuardBench is supported by a [Python library](https://github.com/AmenRa/GuardBench) providing evaluation functionalities on top of it. ## Evaluation Metric Evaluation results are shown in terms of F1. We do not employ the Area Under the Precision-Recall Curve (AUPRC) as we found it overemphasizes models' Precision at the expense of Recall, thus hiding significant performance details. We rely on [Scikit-Learn](https://scikit-learn.org/stable) to compute metric scores. ## Fine-Grained Results Coming soon. ## Reproducibility Coming soon. """ 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"""@inproceedings{guardbench, title = "{G}uard{B}ench: A Large-Scale Benchmark for Guardrail Models", author = "Bassani, Elias and Sanchez, Ignacio", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.emnlp-main.1022", doi = "10.18653/v1/2024.emnlp-main.1022", pages = "18393--18409", }""" CITATION_TEXT = """Copy the following snippet to cite these results. ```bibtex @inproceedings{guardbench, title = "{G}uard{B}ench: A Large-Scale Benchmark for Guardrail Models", author = "Bassani, Elias and Sanchez, Ignacio", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.emnlp-main.1022", doi = "10.18653/v1/2024.emnlp-main.1022", pages = "18393--18409", } ``` """