GitHub • Contribute • Paper • Citation
""" INTRO = """GenCeption is an annotation-free MLLM (Multimodal Large Language Model) evaluation framework that merely requires unimodal data to assess inter-modality semantic coherence and inversely reflects the models' inclination to hallucinate.""" INTRO2 = """This leaderboard displays the evaluated models ranked by their performance on the **GC@3** metric, as defined in [GenCeption: Evaluate Multimodal LLMs with Unlabeled Unimodal Data](https://arxiv.org/abs/2402.14973). For contributing a model evaluation, please submit a pull request on [GitHub](https://github.com/EQTPartners/GenCeption).""" CITATION_BUTTON_LABEL = "Copy the following snippet to cite this benchmark" CITATION_BUTTON_TEXT = r""" @article{cao2023genception, author = {Lele Cao and Valentin Buchner and Zineb Senane and Fangkai Yang}, title = {{GenCeption}: Evaluate Multimodal LLMs with Unlabeled Unimodal Data}, year={2023}, journal={arXiv preprint arXiv:2402.14973}, primaryClass={cs.AI,cs.CL,cs.LG} } """