Text Retrieval
Text retrieval focuses on efficiently finding relevant information within large text corpora, a crucial task for various applications including question answering and knowledge base systems. Current research emphasizes improving retrieval accuracy through advanced ranking models, often incorporating large language models (LLMs) and contrastive learning techniques to refine the selection and ordering of retrieved passages. These advancements are driven by a need for more robust and efficient systems, particularly in handling diverse data types (including multimodal data) and mitigating challenges like adversarial attacks and noisy data. The resulting improvements have significant implications for fields ranging from scientific writing assistance to personalized information access and drug discovery.
Papers
CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
Ye Liu, Rui Meng, Shafiq Jot, Silvio Savarese, Caiming Xiong, Yingbo Zhou, Semih Yavuz
BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?
Zongmeng Zhang, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li