AI 中文总结
提出LAPS方法，通过自蒸馏对齐历史提示并构建锚定提示空间学习任务间关系，在TRACE基准上提升大型语言模型持续适应性能并减少遗忘。
AI 中文摘要
持续适应大型语言模型需要在获取新知识的同时保留先前学习的能力。联合调整模型参数和任务特定的软提示提供了一种有前景的解决方案，但面临两个关键限制：随着模型演变，历史提示可能变得效果较差，而其可迁移的跨任务关系未被显式学习。我们提出学习锚定提示空间（LAPS），该空间保留历史提示的有效性并学习任务特定软提示之间的关系以促进正迁移。LAPS首先通过自蒸馏将历史提示与更新后的模型对齐。然后，LAPS构建一个锚定提示空间，其顶点对应于学习到的任务特定软提示，其中间几何形状由可学习的贝塞尔控制提示塑造。一旦学习到该锚定提示空间，LAPS在验证集上为每个任务识别性能最佳的提示，使优化后的提示能够利用从观察到的任务中获得的知识。在TRACE基准上跨三个Qwen3模型规模的实验表明，LAPS持续优于基于蒸馏、基于提示和联合提示-参数适应的基线，提高了平均性能同时减少了遗忘。
英文摘要
Continually adapting large language models requires acquiring new knowledge while preserving previously learned capabilities. Jointly adapting model parameters and task-specific soft prompts offers a promising solution, but faces two key limitations: historical prompts may become less effective as the model evolves, while their transferable cross-task relationships are not explicitly learned. We propose Learning an Anchored Prompt Space (LAPS), which preserves historical prompt effectiveness and learns relationships among task-specific soft prompts to facilitate positive transfer. LAPS first aligns historical prompts with the updated model through self-distillation. LAPS then constructs an anchored prompt space whose vertices correspond to learned task-specific soft prompts and whose intermediate geometry is shaped by learnable Bézier control prompts. Once this anchored prompt space is learned, LAPS identifies the best-performing prompt for each task on its validation set, allowing the optimized prompt to draw on knowledge acquired from observed tasks. Experiments on the TRACE benchmark across three Qwen3 model scales show that LAPS consistently outperforms distillation-based, prompt-based, and joint prompt--parameter adaptation baselines, improving average performance while reducing forgetting.
