A Survey on Training-free Alignment of Large Language Models

TL;DR

This survey reviews training-free methods for aligning large language models, emphasizing their mechanisms, advantages, limitations, and future challenges to improve model safety and reliability without extensive retraining.

Contribution

It provides the first systematic categorization and analysis of training-free alignment techniques across different stages, aiding future research and practical applications.

Findings

Categorizes TF alignment methods into pre-decoding, in-decoding, and post-decoding stages.

Highlights the mechanisms and limitations of each TF alignment approach.

Identifies key challenges and future directions for TF alignment research.

Abstract

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from knowledge degradation and face challenges in scenarios where the model accessibility or computational resources are constrained. In contrast, training-free (TF) alignment techniques--leveraging in-context learning, decoding-time adjustments, and post-generation corrections--offer a promising alternative by enabling alignment without heavily retraining LLMs, making them adaptable to both open-source and closed-source environments. This paper presents the first systematic review of TF alignment methods, categorizing them by stages of pre-decoding, in-decoding, and post-decoding. For each stage, we provide a detailed examination from the viewpoint of LLMs and multimodal LLMs (MLLMs), highlighting their mechanisms and limitations. Furthermore, we identify key challenges and future directions, paving the way for more inclusive and effective TF alignment techniques. By synthesizing and organizing the rapidly growing body of research, this survey offers a guidance for practitioners and advances the development of safer and more reliable LLMs.