Xiang Qi — accepted AI-conference papers

2024

BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?

Zongmeng Zhang, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li

EMNLP 2024finding

Dense retrieval, which aims to encode the semantic information of arbitrary text into dense vector representations or embeddings, has emerged as an effective and efficient paradigm for text retrieval, consequently becoming an essential component in various natural language processing systems. These…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

Zongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou, Xiang Qi, peng zhang +1

ICML 2024poster

Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect to retrieval augmentation. Despite being supported with external evidence, retrieval-augmented generation still suffers…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗