Kai Zou

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

2025 · arXiv (Cornell University)

Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current …

EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

2019

Jason Wei, Kai Zou. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.