clembench / clembench-leaderboard

Leaderboard to show the evaluted LLMs
https://huggingface.co/spaces/colab-potsdam/clem-leaderboard
MIT License
1 stars 1 forks source link

title: Clembench emoji: 🏆 colorFrom: yellow colorTo: green sdk: gradio sdk_version: 4.40.0 app_file: app.py pinned: false

"clembench: A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents"

@inproceedings{chalamalasetti-etal-2023-clembench,
    title = "clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents",
    author = {Chalamalasetti, Kranti  and
      G{\"o}tze, Jana  and
      Hakimov, Sherzod  and
      Madureira, Brielen  and
      Sadler, Philipp  and
      Schlangen, David},
      booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
      month = dec,
      year = "2023",
      address = "Singapore",
      publisher = "Association for Computational Linguistics",
      url = "https://aclanthology.org/2023.emnlp-main.689",
      pages = "11174--11219"
}