Eurolingua/truthfulqax

Tasks

• text-generation

Citation text from the card

@misc{thellmann2024crosslingual,
    title={Towards Cross-Lingual LLM Evaluation for European Languages},
    author={Klaudia Thellmann and Bernhard Stadler and Michael Fromm and Jasper Schulze Buschhoff and Alex Jude and Fabio Barth and Johannes Leveling and Nicolas Flores-Herr and Joachim Köhler and René Jäkel and Mehdi Ali},
    year={2024},
    eprint={2410.08928},
    archivePrefix={arXiv},
    primaryClass={cs.CL}


# TruthfulQA
@inproceedings{lin-etal-2022-truthfulqa,
    title = "{T}ruthful{QA}: Measuring How Models Mimic Human Falsehoods",
    author = "Lin, Stephanie  and
      Hilton, Jacob  and
      Evans, Owain",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.229",
    doi = "10.18653/v1/2022.acl-long.229",
    pages = "3214--3252",
    abstract = "We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We crafted questions that some humans would answer falsely due to a false belief or misconception. To perform well, models must avoid generating false answe

All datasets marked Permissive or share-alike | JSON