无需标注数据，用模型自身生成信号来优化大模型。
Unsupervised Post-Training of Foundation Models: A Survey
- 利用模型自身输出的统计、关系或目标作为学习信号
- 梳理80种无监督微调方法，揭示信号选择影响性能提升或错误放大
- 提出信号可见性与更新持久性框架，指导模型选型与评估
基础模型的后训练通常依赖人工标签、偏好数据、更强教师模型或可执行验证器。本文研究无监督后训练（UPT）：在无标注输入上进行带更新的适应，其学习信号来自同源模型产物而非外部参考。我们整理了80种严格的UPT方法，并按更新信号来源分为四类：预测统计量、样本关系、自生成目标、内部评估器。除了系统归纳，还揭示信号选择与任务结构如何决定后训练是否提升模型性能或递归放大错误。进一步提出输入可见性 × 更新持久性的正交视角，映射部署场景并构建统一的UPT选择与评估框架。
原文摘要 · Abstract (English)
Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning signal is derived from same-lineage model artifacts rather than an external oracle. We catalog 80 strict UPT methods and organize them by the object that supplies the update signal: a prediction statistic, a sample relation, a self-generated target, or an internal evaluator. Beyond inventory, we show how the choice of internal signal and task structure determines whether post-training improves the model or recursively amplifies error. An orthogonal Input Visibility $\times$ Update Persistence view maps deployment regimes and defines a unified framework for UPT selection and evaluation.
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。