Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
Open Access
- 10 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3931-3941
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (62502486)
- Provincial Natural Science Foundation of Anhui Province (2408085QF193)
- Fundamental Research Funds for the Central Universities of China (WK2150110032)
This publication has 13 references indexed in Scilit:
- CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language ModelsACM Transactions on Information Systems, 2025
- HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction2024
- Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform2024
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- A general tail item representation enhancement framework for sequential recommendationFrontiers of Computer Science, 2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- One Person, One Model—Learning Compound Router for Sequential Recommendation2022
- Towards Automatic Discovering of Deep Hybrid Network Architecture for Sequential Recommendation2022
- Learning Transferable User Representations with Sequential Behaviors via Contrastive Pre-training2021
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019