Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the testing domain during training and online adapts to the testing samples during testing, where the samples are from a fixed domain. We aim to explore a more practical and underexplored scenario, continual test-time adaptation (CTTA) for text understanding, which involves a sequence of testing (unobserved) domains in testing. Current CTTA methods struggle in reducing error accumulation over domains and enhancing generalization to handle unobserved domains: 1) Noise-filtering reduces accumulated errors but discards useful information, and 2) accumulating historical domains enhances generalization, but it is hard to achieve adaptive accumulation. In this paper, we propose a CTTA-T (continual test-time adaptation for text understanding) framework adaptable to evolving target domains: it adopts a teacher-student framework, where the teacher is domain-aware and generalized for evolving domains. To improve teacher predictions, we propose a refine-then-filter based on dropout-driven consistency, which calibrates predictions and removes unreliable guidance. For the adaptation-generalization trade-off, we construct a domain-aware teacher by dynamically accumulating cross-domain semantics via incremental PCA, which continuously tracks domain shifts. Experiments show CTTA-T excels baselines.

翻译：文本理解常受领域偏移影响。为应对测试领域，领域适应（DA）通过训练适应固定且已知的测试领域；更具挑战性的测试时适应（TTA）范式在训练阶段无法接触测试领域，仅在测试时对来自固定领域的样本进行在线适应。本文旨在探索更实用且研究较少的文本理解持续测试时适应（CTTA）场景，其测试阶段涉及一系列未知测试领域的连续出现。现有CTTA方法在减少跨领域误差累积与增强处理未知领域的泛化能力方面存在局限：1）噪声过滤方法虽降低累积误差但丢弃有效信息；2）历史领域累积可增强泛化性，但难以实现自适应累积。本文提出适用于动态目标领域的CTTA-T（文本理解持续测试时适应）框架：采用师生架构，其中教师模块具备领域感知能力并针对演化领域进行广义建模。为提升教师预测质量，提出基于随机丢弃一致性的"校准-过滤"机制，通过预测校准消除不可靠指导。针对适应性与泛化性的权衡，通过增量PCA动态累积跨领域语义构建领域感知教师，持续追踪领域偏移。实验表明CTTA-T显著优于基线方法。