Utilizing large language models for integrating document-level contextual semantic into pseudo-relevance feedback
Authors:
- Min PanMPMin Pan
- Wenrui XiongWXWenrui Xiong
- Yu LiuYLYu Liu
- Junmei WangJWJunmei Wang
- Feng DengFDFeng Deng
- Ellen Anne HuangEHEllen Anne Huang
- Jinguang ChenJCJinguang Chen
- Jimmy X. HuangJHJimmy X. Huang
Open Access
- 26 November 2025
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 333
Abstract
No abstract availableFunding Information
- Natural Sciences and Engineering Research Council of Canada
- Ontario Research Foundation
- National Natural Science Foundation of China (62401189)
- Hubei Provincial Department of Education (2025GA089)
- Hubei Provincial Department of Education (F2023018)
This publication has 21 references indexed in Scilit:
- Enhancing knowledge retrieval with in-context learning and semantic search through generative AIKnowledge-Based Systems, 2025
- A semantic framework for enhancing pseudo-relevance feedback with soft negative sampling and contrastive learningInformation Processing & Management, 2025
- Automatic Text Summarization Method Based on Improved TextRank Algorithm and K-Means ClusteringKnowledge-Based Systems, 2024
- Transformer based contextual text representation framework for intelligent information retrievalExpert Systems with Applications, 2023
- SPRF: A semantic Pseudo-relevance Feedback enhancement for information retrieval via ConceptNetKnowledge-Based Systems, 2023
- Information retrieval from scientific abstract and citation databases: A query-by-documents approach based on Monte-Carlo samplingExpert Systems with Applications, 2022
- A probabilistic framework for integrating sentence-level semantics via BERT into pseudo-relevance feedbackInformation Processing & Management, 2022
- A Pseudo-relevance feedback framework combining relevance matching and semantic matching for information retrievalInformation Processing & Management, 2020
- A simple kernel co‐occurrence‐based enhancement for pseudo‐relevance feedbackJournal of the Association for Information Science and Technology, 2019
- TREC and TIPSTER experiments with inqueryInformation Processing & Management, 1995