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", "Legal Named Entity Recognition (L-NER)") task1 = Task("logiqa", "acc_norm", "Rhetorical Role Prediction (RR)") task2 = Task("logiqa", "acc_norm", "Court Judgment Prediction and Explanation (CJPE)") task3 = Task("logiqa", "acc_norm", "Bail Prediction (BAIL)") task4 = Task("logiqa", "acc_norm", "Legal Statute Identification (LSI)") task5 = Task("logiqa", "acc_norm", "Prior Case Retrieval (PCR)") task6 = Task("logiqa", "acc_norm", "Summarization (SUMM)") # --------------------------------------------------- NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name TITLE = """

IL-TUR Leaderboard

""" # What does your leaderboard evaluate? INTRODUCTION_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: """ EVALUATION_QUEUE_TEXT = """ We encourage submissions for the IL-TUR leaderboard. The leaderboard is open to all researchers and practitioners. Every task has its own leaderboard, and researchers can submit their results for any task. We also encourage submissions for multiple tasks. """ CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" CITATION_BUTTON_TEXT = r""" """