Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Han, Xudong, Yang, Junjie, Wang, Tianyang, Bi, Ziqian, Song, Xinyuan, Hao, Junfeng, Song, Junhao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912718200504320
author Han, Xudong
Yang, Junjie
Wang, Tianyang
Bi, Ziqian
Song, Xinyuan
Hao, Junfeng
Song, Junhao
author_facet Han, Xudong
Yang, Junjie
Wang, Tianyang
Bi, Ziqian
Song, Xinyuan
Hao, Junfeng
Song, Junhao
contents Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline, encompassing (i) data collection methodologies, (ii) full-parameter and parameter-efficient fine-tuning strategies, and (iii) evaluation protocols. We categorized data construction into three major paradigms: expert annotation, distillation from larger models, and self-improvement mechanisms, each offering distinct trade-offs between quality, scalability, and resource cost. Fine-tuning techniques range from conventional supervised training to lightweight approaches, such as low-rank adaptation (LoRA) and prefix tuning, with a focus on computational efficiency and model reusability. We further examine the challenges of evaluating faithfulness, utility, and safety across multilingual and multimodal scenarios, highlighting the emergence of domain-specific benchmarks in healthcare, legal, and financial applications. Finally, we discuss promising directions for automated data generation, adaptive optimization, and robust evaluation frameworks, arguing that a closer integration of data, algorithms, and human feedback is essential for advancing instruction-tuned LLMs. This survey aims to serve as a practical reference for researchers and practitioners seeking to design LLMs that are both effective and reliably aligned with human intentions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17184
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
Han, Xudong
Yang, Junjie
Wang, Tianyang
Bi, Ziqian
Song, Xinyuan
Hao, Junfeng
Song, Junhao
Computation and Language
I.2.7; I.2.6
Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline, encompassing (i) data collection methodologies, (ii) full-parameter and parameter-efficient fine-tuning strategies, and (iii) evaluation protocols. We categorized data construction into three major paradigms: expert annotation, distillation from larger models, and self-improvement mechanisms, each offering distinct trade-offs between quality, scalability, and resource cost. Fine-tuning techniques range from conventional supervised training to lightweight approaches, such as low-rank adaptation (LoRA) and prefix tuning, with a focus on computational efficiency and model reusability. We further examine the challenges of evaluating faithfulness, utility, and safety across multilingual and multimodal scenarios, highlighting the emergence of domain-specific benchmarks in healthcare, legal, and financial applications. Finally, we discuss promising directions for automated data generation, adaptive optimization, and robust evaluation frameworks, arguing that a closer integration of data, algorithms, and human feedback is essential for advancing instruction-tuned LLMs. This survey aims to serve as a practical reference for researchers and practitioners seeking to design LLMs that are both effective and reliably aligned with human intentions.
title Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
topic Computation and Language
I.2.7; I.2.6
url https://arxiv.org/abs/2508.17184