发表机构
Karolinska Institutet; Karolinska University Hospital; KTH Royal Institute of Technology（卡罗林斯卡学院; 卡罗林斯卡大学医院; KTH皇家理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述构建了后训练适应技术的六维分类法，梳理技术间关系，为AI治理提供术语支持，并指出该领域的开放挑战。
AI 中文摘要
后训练适应已成为现代机器学习实践的核心，包括再训练、微调、参数高效适应、对齐、检索增强、模型编辑、遗忘、校准和多模态指令调优等技术。然而，文献在技术家族、模型类别和部署场景方面仍呈碎片化，难以比较方法或描述已训练模型的修改情况。本综述综合后训练适应文献，引入了由机制、目标、数据需求、持久性、结构范围和模型类型构成的六维分类法。该分类法区分了常被混淆的术语，如微调、检索增强和提示，并展示了适应策略如何从传统机器学习发展到深度学习、基础模型、大语言模型和多模态大语言模型。它还绘制了技术间的关系，包括继承、替代、混合和分层部署栈。形成的术语可支持技术文档、模型变更跟踪和治理分析。本综述最后指出了评估、可复现性、持久推理时适应、遗忘、多模态适应和治理感知后训练工作流方面的开放挑战。
英文摘要
Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning. However, the literature remains fragmented across technique families, model classes, and deployment contexts, making it difficult to compare methods or describe how a trained model has been modified. This survey synthesizes the post-training adaptation literature and introduces a six-dimensional taxonomy organized by mechanism, goal, data requirement, persistence, structural scope, and model type. The taxonomy distinguishes commonly conflated terms such as fine-tuning, retrieval augmentation, and prompting, and shows how adaptation strategies evolve from traditional machine learning through deep learning, foundation models, large language models, and multimodal large language models. It also maps relationships among techniques, including inheritance, supersession, hybridization, and layered deployment stacks. The resulting vocabulary can support technical documentation, model-change tracking, and governance analysis. The survey concludes by identifying open challenges in evaluation, reproducibility, persistent inference-time adaptation, unlearning, multimodal adaptation, and governance-aware post-training workflows.
