RRRA：通过检索器适配器进行重采样与重排序
RRRA: Resampling and Reranking through a Retriever Adapter
AI总结：
本文提出可学习适配器模块RRRA，动态估计难负例为假负例的概率，并用于训练重采样与推理重排序，在标准基准上一致超越强双编码器基线。
摘要：
在稠密检索中，有效训练的关键在于选择高质量难负例，同时避免假负例。近期方法基于正文档分数应用启发式规则来识别难负例，从而提升了性能和可解释性。然而，这些全局的、与具体示例无关的策略往往会遗漏实例特定的假负例。为解决这一问题，我们提出一个可学习的适配器模块，该模块监控双编码器（Bi-Encoder）表示，以估计某个难负例实际上是假负例的可能性。该概率被动态且上下文相关地建模，从而支持细粒度、针对具体查询的判断。预测分数被用于两个下游组件：（1）重采样，在训练过程中对负例进行重新加权；（2）重排序，在推理时对前k个检索到的文档进行重新排序。在标准基准上的实验结果表明，我们提出的适配器增强框架一致优于强双编码器基线，凸显了在稠密检索中显式建模假负例的益处。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
