基于不确定性迭代采样，提升信息检索领域自适应效果
UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval
- 按模型不确定性分层筛选文档，优先处理不确定样本
- 小样本下提升2.45~3.49 nDCG@10，平均仅需4k样本
- 适合低资源场景下的检索模型跨域迁移
无监督领域自适应通过在目标域文档上生成伪查询，将神经检索器泛化至未知领域。该过程的性能与效率高度依赖于伪查询生成所用文档的选择。现有文档采样方法侧重多样性，但忽略了模型不确定性。本文提出不确定性迭代采样方法UnIte，通过（1）过滤高随机性不确定性文档，（2）优先选择高认知不确定性文档，以最大化当前模型的学习效用。我们在BEIR大规模语料库上对小模型和大模型进行了大量实验，结果显示，在平均仅4000个样本的条件下，取得+2.45和+3.49的nDCG@10显著提升。
原文摘要 · Abstract (English)
Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for pseudo query generation. The existing document sampling method focuses on diversity but fails to capture model uncertainty. In contrast, we propose **Un**certainty-based **Ite**rative Document Sampling (UnIte) addressing these limitations by (1) filtering documents with high aleatoric uncertainty and (2) prioritizing those with high epistemic uncertainty, maximizing the learning utility of the current model. We conducted extensive experiments on a large corpus of BEIR with small and large models, showing significant gains of +2.45 and +3.49 nDCG@10 with a smaller training sample size, 4k on average.
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。