ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding
Citations Over TimeTop 10% of 2023 papers
Abstract
We introduce ZeroSCROLLS, a zero-shot benchmark for natural language understanding over long texts, which contains only test and small validation sets, without training data. We adapt six tasks from the SCROLLS benchmark, and add four new datasets, including two novel information fusing tasks, such as aggregating the percentage of positive reviews. Using ZeroSCROLLS, we conduct a comprehensive evaluation of both open-source and closed large language models, finding that Claude outperforms ChatGPT, and that GPT-4 achieves the highest average score. However, there is still room for improvement on multiple open challenges in ZeroSCROLLS, such as aggregation tasks, where models struggle to pass the naive baseline. As the state of the art is a moving target, we invite researchers to evaluate their ideas on the live ZeroSCROLLS leaderboard.
Related Papers
- → Study on viewer’s preference of sensibility vocabulary depending on composition of portrait shot in image -Mainly on the basis of size and placement of shot-(2021)1 cited
- → <title>High-speed photographic study on shot put</title>(1995)
- Study on Shot and be Shot Skills of Our Men Soccer Player from the World Cup(2002)
- Study and application of telecom operators system security state baseline(2012)
- → Take a Shot: Part 1(2017)