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") NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name TITLE = """

🪷 LOTUS: Detailed LVLM Evaluation from Quality to Societal Bias

""" # What does your leaderboard evaluate? INTRODUCTION_TEXT = """ We introduce **LOTUS**, a leaderboard for evaluating detailed captions, addressing three main gaps in existing evaluations: lack of **standardized** criteria, **bias-aware** assessments, and **user preference** considerations. LOTUS comprehensively evaluates various aspects, including caption quality (e.g., alignment, descriptiveness), risks (e.g., hallucination), and societal biases (e.g., gender bias) while enabling preference-oriented evaluations by tailoring criteria to diverse user preferences. """ # Which evaluations are you running? how can people reproduce what you have? LLM_BENCHMARKS_TEXT = """ Details about the LLM benchmarks will go here. """ EVALUATION_QUEUE_TEXT = """ ## Evaluation Queue and Submission Models are evaluated on the private test set of COCO Captions, and results are protected from misuse. **To submit your model for evaluation, please follow these steps:** 1. **Prepare your model's predictions**: Ensure your model's predictions are in the same format as the COCO Captions [dataset](https://cocodataset.org/#format-data). 2. **Submit via our form**: Fill out the [submission form](https://forms.gle/your_form_link_here) with your model details and prediction file. 3. **Wait for results**: The evaluation may take some time. Results will be updated on the leaderboard. For any issues or questions, please open an issue on our [GitHub repository](https://github.com/lotus-benchmark/lotus). """ CITATION_BUTTON_LABEL = "BibTeX" # Keep this label or change if needed CITATION_BUTTON_TEXT = """ @inproceedings{hirota2025lotus, author = {Yusuke Hirota and Boyi Li and Ryo Hachiuma and Yueh-Hua Wu and Boris Ivanovic and Yuta Nakashima and Marco Pavone and Yejin Choi and Yu-Chiang Frank Wang and Huck Yang}, title = {LOTUS: {A} Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences}, booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2025} } """