%0 Conference Paper %1 pfister-hotho-2024-supergleber %A Pfister, Jan %A Hotho, Andreas %B Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) %C Mexico City, Mexico %D 2024 %E Duh, Kevin %E Gomez, Helena %E Bethard, Steven %I Association for Computational Linguistics %K myown author:hotho author:pfister from:janpf %P 7897--7916 %T SuperGLEBer: German Language Understanding Evaluation Benchmark %U https://aclanthology.org/2024.naacl-long.438 %X We assemble a broad Natural Language Understanding benchmark suite for the German language and consequently evaluate a wide array of existing German-capable models in order to create a better understanding of the current state of German LLMs. Our benchmark consists of 29 different tasks ranging over different types such as document classification, sequence tagging, sentence similarity, and question answering, on which we evaluate 10 different German-pretrained models, thereby charting the landscape of German LLMs. In our comprehensive evaluation we find that encoder models are a good choice for most tasks, but also that the largest encoder model does not necessarily perform best for all tasks. We make our benchmark suite and a leaderboard publically available at https://supergleber.professor-x.de and encourage the community to contribute new tasks and evaluate more models on it (https://github.com/LSX-UniWue/SuperGLEBer).

@inproceedings{pfister-hotho-2024-supergleber, abstract = {We assemble a broad Natural Language Understanding benchmark suite for the German language and consequently evaluate a wide array of existing German-capable models in order to create a better understanding of the current state of German LLMs. Our benchmark consists of 29 different tasks ranging over different types such as document classification, sequence tagging, sentence similarity, and question answering, on which we evaluate 10 different German-pretrained models, thereby charting the landscape of German LLMs. In our comprehensive evaluation we find that encoder models are a good choice for most tasks, but also that the largest encoder model does not necessarily perform best for all tasks. We make our benchmark suite and a leaderboard publically available at https://supergleber.professor-x.de and encourage the community to contribute new tasks and evaluate more models on it (https://github.com/LSX-UniWue/SuperGLEBer).}, added-at = {2024-06-17T03:26:45.000+0200}, address = {Mexico City, Mexico}, author = {Pfister, Jan and Hotho, Andreas}, biburl = {https://www.bibsonomy.org/bibtex/242ab72c3a9e02859fcf17f97d725cd06/dmir}, booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)}, editor = {Duh, Kevin and Gomez, Helena and Bethard, Steven}, interhash = {baa9812991a37bd4cf420b880fde7d6d}, intrahash = {42ab72c3a9e02859fcf17f97d725cd06}, keywords = {myown author:hotho author:pfister from:janpf}, month = {06}, pages = {7897--7916}, publisher = {Association for Computational Linguistics}, timestamp = {2024-06-17T03:26:45.000+0200}, title = {{S}uper{GLEB}er: {G}erman Language Understanding Evaluation Benchmark}, url = {https://aclanthology.org/2024.naacl-long.438}, year = 2024 }