用梯度范数检测文档库是否偏离原分布，提前预警检索模型更新时机。
When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR
- 通过梯度范数无监督判断新文档集是否偏离原始分布。
- 在BEIR基准上显著提升检索鲁棒性与效率，避免性能下降。
- 适合需要长期维护的动态知识库系统，如新闻、科研数据库。
密集检索器将文本编码为嵌入向量，以高效响应用户查询从大规模数据库中检索相关文档。然而真实世界的文档库持续演进，导致其分布偏离检索器训练时的原始分布。若不及时更新或重训练，索引新出现的内容可能降低未来查询的检索效果。因此，识别密集检索器是否需要更新至关重要。本文提出一个新任务：在索引前预测文档库是否相对于检索器处于分布外（OOD）。该方法可主动管理检索器更新，防止潜在检索失败。我们提出GradNormIR，一种利用梯度范数的无监督方法，有效检测分布外文档集。在BEIR基准上的实验表明，GradNormIR能及时更新密集检索器，显著提升在动态文档集合中的检索鲁棒性与效率。
原文摘要 · Abstract (English)
Dense retrievers encode texts into embeddings to efficiently retrieve relevant documents from large databases in response to user queries. However, real-world corpora continually evolve, leading to a shift from the original training distribution of the retriever. Without timely updates or retraining, indexing newly emerging documents can degrade retrieval performance for future queries. Thus, identifying when a dense retriever requires an update is critical for maintaining robust retrieval systems. In this paper, we propose a novel task of predicting whether a corpus is out-of-distribution (OOD) relative to a dense retriever before indexing. Addressing this task allows us to proactively manage retriever updates, preventing potential retrieval failures. We introduce GradNormIR, an unsupervised approach that leverages gradient norms to detect OOD corpora effectively. Experiments on the BEIR benchmark demonstrate that GradNormIR enables timely updates of dense retrievers in evolving document collections, significantly enhancing retrieval robustness and efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。