LLM-VPRF：基于大语言模型的向量伪相关反馈
LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback
AI总结：
本文提出LLM-VPRF，将向量伪相关反馈技术扩展至基于大语言模型的稠密检索器，通过多基准数据集验证了其能跨不同LLM架构稳健提升检索性能。
摘要：
向量伪相关反馈（VPRF）通过迭代优化查询表示，在改进基于BERT的稠密检索系统方面展现出可喜的结果。本文研究了VPRF对基于大语言模型（LLM）的稠密检索器的泛化能力。我们引入了LLM-VPRF，并在多个基准数据集上评估了其有效性，分析了不同LLM对反馈机制的影响。结果表明，VPRF的益处成功扩展到LLM架构，证明其成为增强稠密检索性能的稳健技术，而不受底层模型限制。这项工作弥合了基于BERT的稠密检索器与现代LLM之间的VPRF差距，并为其未来方向提供了见解。
英文摘要：
Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This paper investigates the generalizability of VPRF to Large Language Model (LLM) based dense retrievers. We introduce LLM-VPRF and evaluate its effectiveness across multiple benchmark datasets, analyzing how different LLMs impact the feedback mechanism. Our results demonstrate that VPRF's benefits successfully extend to LLM architectures, establishing it as a robust technique for enhancing dense retrieval performance regardless of the underlying models. This work bridges the gap between VPRF with traditional BERT-based dense retrievers and modern LLMs, while providing insights into their future directions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
