RRRA: Resampling and Reranking through a Retriever Adapter

Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance and interpretability. However, these global, example-agnostic strategies often miss instance-specific false negatives. To address this, we propose a learnable adapter module that monitors Bi-Encoder representations to estimate the likelihood that a hard negative is actually a false negative. This probability is modeled dynamically and contextually, enabling fine-grained, query-specific judgments. The predicted scores are used in two downstream components: (1) resampling, where negatives are rewei-ghted during training, and (2) reranking, where top-k retrieved documents are reordered at inference. Empirical results on standard benchmarks show that our adapter-enhanced framework consistently outperforms strong Bi-Encoder baselines, underscoring the benefit of explicit false negative modeling in dense retrieval.