RRRA: Resampling and Reranking through a Retriever Adapter
This addresses a specific bottleneck in dense retrieval training for information retrieval systems, offering an incremental improvement over existing methods.
The paper tackles the problem of false negatives in dense retrieval training by proposing a learnable adapter module that dynamically estimates the likelihood of hard negatives being false negatives, enabling query-specific judgments. Results show the adapter-enhanced framework consistently outperforms strong Bi-Encoder baselines on standard benchmarks.
In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. 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 reweighted 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.