Abstract
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 these issues, we propose a planning framework for constructing Extractive-based LLMs called 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 GitHub.
Blogger's Review: PlanE offers a systematic approach to optimize LLM's task adaptability, especially in the context of high annotation costs. The introduction of the DTI planner is particularly significant, providing a new direction for future LLM research with its flexibility and efficiency.