InsBank: Evolving Instruction Subset for Ongoing Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Jiayi, Li, Yiwei, Feng, Shaoxiong, Yuan, Peiwen, Wang, Xinglin, Zhang, Yueqi, Tan, Chuyi, Pan, Boyuan, Ren, Huan, Hu, Yao, Li, Kan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912561230774272
author Shi, Jiayi
Li, Yiwei
Feng, Shaoxiong
Yuan, Peiwen
Wang, Xinglin
Zhang, Yueqi
Tan, Chuyi
Pan, Boyuan
Ren, Huan
Hu, Yao
Li, Kan
author_facet Shi, Jiayi
Li, Yiwei
Feng, Shaoxiong
Yuan, Peiwen
Wang, Xinglin
Zhang, Yueqi
Tan, Chuyi
Pan, Boyuan
Ren, Huan
Hu, Yao
Li, Kan
contents Large language models (LLMs) typically undergo instruction tuning to enhance alignment. Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs. However, how to evolve these selected subsets alongside the development of new instruction data remains insufficiently explored. To achieve LLMs' ongoing alignment, we introduce Instruction Bank (\textbf{InsBank}), a continuously updated repository that integrates the latest valuable instruction data. We further propose Progressive Instruction Bank Evolution (\textbf{PIBE}), a novel framework designed to evolve InsBank effectively and efficiently over time. PIBE employs a gradual data selection strategy to maintain long-term efficiency, leveraging a representation-based diversity score to capture relationships between data points and retain historical information for comprehensive diversity evaluation. This also allows for flexible combination of diversity and quality scores during data selection and ranking. Extensive experiments demonstrate that PIBE significantly outperforms baselines in InsBank evolution and is able to extract budget-specific subsets, demonstrating its effectiveness and adaptability.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11419
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InsBank: Evolving Instruction Subset for Ongoing Alignment
Shi, Jiayi
Li, Yiwei
Feng, Shaoxiong
Yuan, Peiwen
Wang, Xinglin
Zhang, Yueqi
Tan, Chuyi
Pan, Boyuan
Ren, Huan
Hu, Yao
Li, Kan
Computation and Language
Large language models (LLMs) typically undergo instruction tuning to enhance alignment. Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs. However, how to evolve these selected subsets alongside the development of new instruction data remains insufficiently explored. To achieve LLMs' ongoing alignment, we introduce Instruction Bank (\textbf{InsBank}), a continuously updated repository that integrates the latest valuable instruction data. We further propose Progressive Instruction Bank Evolution (\textbf{PIBE}), a novel framework designed to evolve InsBank effectively and efficiently over time. PIBE employs a gradual data selection strategy to maintain long-term efficiency, leveraging a representation-based diversity score to capture relationships between data points and retain historical information for comprehensive diversity evaluation. This also allows for flexible combination of diversity and quality scores during data selection and ranking. Extensive experiments demonstrate that PIBE significantly outperforms baselines in InsBank evolution and is able to extract budget-specific subsets, demonstrating its effectiveness and adaptability.
title InsBank: Evolving Instruction Subset for Ongoing Alignment
topic Computation and Language
url https://arxiv.org/abs/2502.11419