PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs
Quick Answer
The PlanE framework enhances extractive-based LLMs by optimizing data decomposition, instruction tuning, and prompt inference, significantly reducing annotation costs.
Quick Take
The Data-Tuning-Inference (DTI) planner selects optimal base- combinations, improving efficiency across various datasets and models, as demonstrated by experimental results.
Key Points
- PlanE integrates data decomposition, instruction tuning, and prompt inference for LLM optimization.
- The DTI planner selects optimal base-LLM combinations for specific datasets.
- Experimental results validate PlanE's effectiveness across various datasets and models.
- The framework aims to reduce the high annotation costs associated with LLM tuning.
- Code for PlanE is publicly available for further research and development.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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 this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.20470 [cs.AI] |
| (or arXiv:2607.20470v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.20470 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Weiyan Zhang [view email]
[v1]
Fri, 22 May 2026 13:37:33 UTC (1,197 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.