Controllable Text Generation for Large Language Models: A Survey

TL;DR

This survey comprehensively reviews controllable text generation techniques for large language models, categorizing methods, discussing evaluation, applications, challenges, and future directions to guide researchers and developers.

Contribution

It provides a systematic overview of CTG methods, clarifies core concepts, categorizes tasks, and analyzes advantages and limitations, offering valuable guidance for future research.

Findings

Categorization of CTG tasks into content and attribute control

Analysis of model retraining, fine-tuning, reinforcement learning, prompt engineering, latent space manipulation, and decoding interventions

Identification of key challenges like reduced fluency and practicality

Abstract

In Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated high text generation quality. However, in real-world applications, LLMs must meet increasingly complex requirements. Beyond avoiding misleading or inappropriate content, LLMs are also expected to cater to specific user needs, such as imitating particular writing styles or generating text with poetic richness. These varied demands have driven the development of Controllable Text Generation (CTG) techniques, which ensure that outputs adhere to predefined control conditions--such as safety, sentiment, thematic consistency, and linguistic style--while maintaining high standards of helpfulness, fluency, and diversity. This paper systematically reviews the latest advancements in CTG for LLMs, offering a comprehensive definition of its core concepts and clarifying the requirements for control conditions and text quality. We categorize CTG tasks into two primary types: content control and attribute control. The key methods are discussed, including model retraining, fine-tuning, reinforcement learning, prompt engineering, latent space manipulation, and decoding-time intervention. We analyze each method's characteristics, advantages, and limitations, providing nuanced insights for achieving generation control. Additionally, we review CTG evaluation methods, summarize its applications across domains, and address key challenges in current research, including reduced fluency and practicality. We also propose several appeals, such as placing greater emphasis on real-world applications in future research. This paper aims to offer valuable guidance to researchers and developers in the field. Our reference list and Chinese version are open-sourced at https://github.com/IAAR-Shanghai/CTGSurvey.