拖放式大型語言模型：零樣本提示到權重轉換

摘要

現代參數高效微調（PEFT）方法，如低秩適應（LoRA），降低了定制大型語言模型（LLMs）的成本，但仍需針對每個下游數據集進行單獨的優化運行。我們引入了拖放式LLMs（\textit{DnD}），這是一種提示條件參數生成器，通過將少量未標記的任務提示直接映射到LoRA權重更新，從而消除了每任務訓練的需求。一個輕量級文本編碼器將每個提示批次蒸餾成條件嵌入，然後通過級聯的超卷積解碼器轉換為完整的LoRA矩陣集。一旦在多樣化的提示-檢查點對集合中進行訓練，DnD能在幾秒內生成任務特定參數，實現：i) 相比全微調降低高達12,000倍的成本，ii) 在未見的常識推理、數學、編碼和多模態基準測試中，平均性能提升高達30%，iii) 儘管從未見過目標數據或標籤，仍能實現穩健的跨域泛化。我們的結果表明，提示條件參數生成是基於梯度適應快速專用化LLMs的可行替代方案。我們的項目可在https://jerryliang24.github.io/DnD{https://jerryliang24.github.io/DnD}查看。

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}.

拖放式大型語言模型：零樣本提示到權重轉換

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

摘要

Support