Blending Learning To Rank And Dense Representations For Efficient And Effective Cascades

Abstract

We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are complemented and integrated with 253 hand-crafted lexical features extracted from the same corpus. Blending of the relevance signals from the two different groups of features is learned by a classical Learning-to-Rank (LTR) model based on a forest of decision trees. To evaluate our solution, we employ a pipelined architecture where a dense neural retriever serves as the first stage and performs a nearest-neighbor search over the neural representations of the documents. Our LTR model acts instead as the second stage that re-ranks the set of candidates retrieved by the first stage to enhance effectiveness. The results of reproducible experiments conducted with state-of-the-art dense retrievers on publicly available resources show that the proposed soluti

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynardini2025blending

Related papers

• Pseudo-relevance Feedback For Multiple Representation Dense Retrieval (2021)12.93
• LIDER: An Efficient High-dimensional Learned Index For Large-scale Dense Passage Retrieval (2022)0.00
• Bayesian Active Learning With Gaussian Processes Guided By LLM Relevance Scoring For Dense Passage Retrieval (2026)0.00
• Investigating Multi-layer Representations For Dense Passage Retrieval (2025)0.00
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Densifying Sparse Representations For Passage Retrieval By Representational Slicing (2021)0.00
• A Passage-based Approach To Learning To Rank Documents (2019)8.60
• On Approximate Nearest Neighbour Selection For Multi-stage Dense Retrieval (2021)8.35