top of page
About
Contact

ZeroSCROLLS: Zero-Shot CompaRison Over Long Language Sequences

​

What is Zero-SCROLLS?

ZeroSCROLLS is a suite of datasets that require synthesizing information over long texts. The benchmark includes ten natural language tasks across multiple domains, including summarization, question answering, aggregated sentiment classification and information reordering.

​

​

​

​

Citing ZeroSCROLLS

Please use the following bibliography to cite ZeroSCROLLS:

@misc{shaham2023zeroscrolls,
      title={ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding}, 
      author={Uri Shaham and Maor Ivgi and Avia Efrat and Jonathan Berant and Omer Levy},
      year={2023},
      eprint={2305.14196},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

When citing ZeroSCROLLS, please make sure to cite all of the original dataset papers. [bibtex]

​

Contact Us

scrolls-benchmark-contact@googlegroups.com

Tel-Aviv University NLP lab
bottom of page