拖放式大语言模型：零样本提示到权重转换

摘要

现代参数高效微调（PEFT）方法，如低秩适应（LoRA），降低了定制大型语言模型（LLMs）的成本，但仍需为每个下游数据集进行单独的优化训练。我们提出了拖放式LLMs（\textit{DnD}），一种基于提示的参数生成器，通过将少量未标注的任务提示直接映射到LoRA权重更新，从而消除了逐任务训练的需求。一个轻量级文本编码器将每批提示提炼为条件嵌入，随后通过级联的超卷积解码器转换为完整的LoRA矩阵集。一旦在多样化的提示-检查点对集合中完成训练，DnD能在数秒内生成任务特定参数，带来以下优势：i) 相比全量微调，开销降低高达12,000倍；ii) 在未见过的常识推理、数学、编程及多模态基准测试中，平均性能提升高达30%，超越最强的训练LoRAs；iii) 尽管从未接触目标数据或标签，仍展现出强大的跨领域泛化能力。我们的结果表明，基于提示的参数生成是快速定制LLMs的可行替代方案，相较于基于梯度的适应方法。项目详情请访问https://jerryliang24.github.io/DnD{https://jerryliang24.github.io/DnD}。

English

Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate optimization run for every downstream dataset. We introduce Drag-and-Drop LLMs (\textit{DnD)}, a prompt-conditioned parameter generator that eliminates per-task training by mapping a handful of unlabeled task prompts directly to LoRA weight updates. A lightweight text encoder distills each prompt batch into condition embeddings, which are then transformed by a cascaded hyper-convolutional decoder into the full set of LoRA matrices. Once trained in a diverse collection of prompt-checkpoint pairs, DnD produces task-specific parameters in seconds, yielding i) up to 12,000times lower overhead than full fine-tuning, ii) average gains up to 30\% in performance over the strongest training LoRAs on unseen common-sense reasoning, math, coding, and multimodal benchmarks, and iii) robust cross-domain generalization despite never seeing the target data or labels. Our results demonstrate that prompt-conditioned parameter generation is a viable alternative to gradient-based adaptation for rapidly specializing LLMs. Our project is available at https://jerryliang24.github.io/DnD{https://jerryliang24.github.io/DnD}.

拖放式大语言模型：零样本提示到权重转换

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

摘要

Support