让用户提示词跨模型迁移，省下98%重训成本
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
- 用轻量适配器桥接不同模型语义差距
- 迁移性能媲美甚至超越从头重训
- 适合需长期维护个性化AI的开发者
大型语言模型的个性化常依赖用户专属的软提示（soft prompts），但当基础模型升级时，这些提示会失效，需耗费大量资源重新训练。为此，我们提出提示级用户迁移适配器（PUMA），一种轻量级框架，可高效实现跨不兼容模型的个性化提示迁移。PUMA通过参数高效的适配器弥合语义鸿沟，并结合基于分组的用户选择策略，显著降低训练成本。在三个大规模数据集上的实验表明，该方法性能与从头重训相当甚至更优，计算成本最高降低98%。框架在多种模型架构间表现出强泛化能力，且在链式和聚合迁移等复杂场景中依然稳健，为个性化AI的可持续演进提供了可行路径，实现了用户资产与底层模型的解耦。
原文摘要 · Abstract (English)
Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this limitation, we propose the Prompt-level User Migration Adapter (PUMA), a lightweight framework to efficiently migrate personalized prompts across incompatible models. PUMA utilizes a parameter-efficient adapter to bridge the semantic gap, combined with a group-based user selection strategy to significantly reduce training costs. Experiments on three large-scale datasets show our method matches or even surpasses the performance of retraining from scratch, reducing computational cost by up to 98%. The framework demonstrates strong generalization across diverse model architectures and robustness in advanced scenarios like chained and aggregated migrations, offering a practical path for the sustainable evolution of personalized AI by decoupling user assets from the underlying models.
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。