DPR-FL: A Dual-Path Retrieval Method with Fusion-Based Filtering and LLM Feedback

Abstract

: Faced with the surge of massive natural-language content, information retrieval systems must handle increasingly complex queries while filtering noisy information effectively. Although conventional approaches have made notable progress in matching efficiency and general adaptability, they still struggle to precisely model deep semantic associations between query intent and documents in real-world environments. Such limitations can lead to ranking deviations and omission of critical information. Motivated by recent advances in large language models (LLMs) and their capability to capture deep semantics, we propose DPR-FL , a Dual-Path Retrieval method that integrates fusion-based Filtering with structured LLM Feedback . It combines direct retrieval with a generation-guided retrieval process to form cooperative information flows. By fusing candidate results from multiple sources, applying a high-dimensional semantic filtering strategy, and leveraging LLM-based semantic feedback, DPR-FL refines and optimizes the selection of relevant documents, improving both coverage and relevance. Furthermore, the framework supports adaptive weighting of candidate sources and semantic signals, enhancing robustness in heterogeneous retrieval scenarios. Together, these components enable finer-grained information selection and semantic enrichment, substantially improving retrieval performance and result reliability in complex contexts. Experimental evaluations on standard web search benchmarks, including TREC DL’19 and DL’20, as well as low-resource BEIR datasets, demonstrate that DPR-FL achieves measurable gains across key metrics such as NDCG@10 and MAP, showing improved generalization, robustness, and adaptability in zero-shot retrieval settings.