Information retrieval plays a crucial role in resource localization. Current dense retrievers retrieve the relevant documents within a corpus via embedding similarities, which compute similarities between dense vectors mainly depending on word co-occurrence between queries and documents, but overlook the real query intents.
View on arXiv@article{xu2025_2505.22299,
title={ Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries },
author={ Ganlin Xu and Zhoujia Zhang and Wangyi Mei and Jiaqing Liang and Weijia Lu and Xiaodong Zhang and Zhifei Yang and Xiaofeng Ma and Yanghua Xiao and Deqing Yang },
journal={arXiv preprint arXiv:2505.22299},
year={ 2025 }
}