EMNLP Findings2025
RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
Qingsong Lv, Yangning Li, Zihua Lan, Zishan Xu, Jiwei Tang, Tingwei Lu, Yinghui Li, Wenhao Jiang, Hong-Gee Kim, Hai-Tao Zheng, Philip S. Yu
Abstract
Instruction tuning of large language models (LLMs) benefits more from a handful of highquality examples than from hordes of lowquality ones. Existing selection methods typically rely on static, heuristic quality scores and are executed only once before training. Consequently, they neither adapt to the changing state of the model nor target downstream objectives, leaving substantial room for optimization. We propose RAISE (Reinforced Adaptive Instruction SElection), a dynamic, task-driven framework that integrates selection into every training step. At each step, RAISE estimates the expected contribution of each candidate instruction to task performance and admits only the most helpful. By modeling this process as sequential decision making, we optimize the selector with reinforcement learning, yielding an interpretable policy specialized for the target task. Extensive experiments show that RAISE reaches comparable or better results than fulldata training while updating only 1% of the steps, demonstrating both high efficacy and significant computational savings.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites UnifiedQA: Crossing Format Boundaries With a Single QA System
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites Finetuned Language Models are Zero-Shot Learners
- LESS: Selecting Influential Data for Targeted Instruction Tuning cites The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
- LESS: Selecting Influential Data for Targeted Instruction Tuning cites Finetuned Language Models are Zero-Shot Learners
- LIMA: Less Is More for Alignment cites Finetuned Language Models are Zero-Shot Learners
- Finetuned Language Models are Zero-Shot Learners cites UnifiedQA: Crossing Format Boundaries With a Single QA System
Builds on14
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- LIMA: Less Is More for AlignmentChunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer et al.NeurIPS 2023 · 1,486 citations
- The Flan Collection: Designing Data and Methods for Effective Instruction TuningShayne Longpre, Le Hou, Tu Vu, Albert Webson et al.ICML 2023 · 908 citations
- UnifiedQA: Crossing Format Boundaries With a Single QA SystemDaniel Khashabi, Sewon Min, Tushar Khot, Ashish Sabharwal et al.EMNLP Findings 2020 · 514 citations
- LESS: Selecting Influential Data for Targeted Instruction TuningMengzhou Xia, Sadhika Malladi, Suchin Gururangan, Sanjeev Arora et al.ICML 2024 · 460 citations
Related papers
- ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction TuningYang Wu, Huayi Zhang, Yizheng Jiao, Lin Ma et al.EMNLP Findings 2025
- RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data SelectionYixin Yang, Qingxiu Dong, Linli Yao, Fangwei Zhu et al.AAAI 2026
- From Selection to Refinement: Iterative Optimization for Instruction DataHang Hu, Ziyan Liu, Rujie Wen, Ruihui Hou et al.ACL 2026
- BRIEF: Bi-level Coreset Selection for Efficient Instruction Tuning in LLMsChaoyuan Shen, Chi Zhang, Chengliang Chai, Jiacheng Wang et al.VLDB 2026 · 2 citations
- LEAD: Iterative Data Selection for Efficient LLM Instruction TuningXiaotian Lin, Yanlin Qi, Yizhang Zhu, Themis Palpanas et al.VLDB 2026 · 16 citations
