Refit: Relevance Feedback From A Reranker During Inference

Abstract

Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model. While the reranker often yields improved candidate scores compared to the retriever, its scope is confined to only the top K retrieved candidates. As a result, the reranker cannot improve retrieval performance in terms of Recall@K. In this work, we propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time. Specifically, given a test instance during inference, we distill the reranker's predictions for that instance into the retriever's query representation using a lightweight update mechanism. The aim of the distillation loss is to align the retriever's candidate scores more closely with those produced by the reranker. The algorithm then proceeds by executing a second retrieval step

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyreddy2023refit

Related papers

• Drowning In Documents: Consequences Of Scaling Reranker Inference (2024)0.00
• RRRA: Resampling And Reranking Through A Retriever Adapter (2025)0.00
• Rank-k: Test-time Reasoning For Listwise Reranking (2025)0.00
• Towards Robust Ranker For Text Retrieval (2022)5.84
• A Deep Learning Approach For Selective Relevance Feedback (2024)6.34
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Rebol: Retrieval Via Bayesian Optimization With Batched LLM Relevance Observations And Query Reformulation (2026)0.00
• Improving Query Representations For Dense Retrieval With Pseudo Relevance Feedback: A Reproducibility Study (2021)7.16