提出PlanE框架，高效构建提取式大模型
PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs
- 分步规划数据、微调与提示推理流程
- 在多个数据集上提升模型性能，效率更高
- 适配不同任务需求，适合想定制LLM的开发者
提升大语言模型（LLMs）的任务特定能力通常依赖大量指令微调数据，但数据量庞大导致标注成本高，且缺乏针对具体任务的优化方法。为此，我们提出一种用于构建提取式大模型的 extbf{Plan}ning框架—— extbf{PlanE}，包含数据分解、指令微调和提示推理三个阶段。此外，我们设计了数据-微调-推理（DTI）规划器，用于为特定数据集选择最优的基础模型及其DTI组合，以提高构建效率。实验结果表明，PlanE在使用相同基础模型时跨不同数据集有效，在使用不同基础模型时对同一数据集也表现良好。同时，我们验证了DTI规划器在多种优化目标下的泛化能力。代码已公开于https://github.com/gugugu-469/PlanE。
原文摘要 · Abstract (English)
Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets. However, the sheer volume of such data imposes a considerable annotation cost, and a lack of optimization methods for tailoring LLMs to specific tasks. To address the above issues, we propose a \textbf{Plan}ning framework for constructing \textbf{E}xtractive-based LLMs called \textbf{PlanE}, which includes data decomposition, instruction tuning, and prompt inference. Additionally, we introduce a Data-Tuning-Inference (DTI) planner, aimed at selecting the optimal base-LLM and its DTI combinations for specific datasets to improve construction efficiency. The experimental results demonstrate the effectiveness of our PlanE from two views: (1) across different datasets using the same base-LLM, and (2) on the same dataset using different base-LLMs. Furthermore, we validate the generalizability of the proposed DTI planner under different optimization objectives. The codes are publicly available at https://github.com/gugugu-469/PlanE.
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。