ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding
This work addresses the need for robust evaluation benchmarks for long text understanding in AI research, but it is incremental as it adapts existing tasks and adds new datasets.
The authors tackled the problem of evaluating long text understanding in natural language processing by introducing ZeroSCROLLS, a zero-shot benchmark without training data, and found that GPT-4 achieved the highest average score among large language models, though models still struggled on tasks like aggregation, failing to pass naive baselines.
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.