# Controllable Text Generation for Large Language Models: A Survey

arXiv: https://arxiv.org/abs/2408.12599 · HTML: https://mlsanity.com/paper/2408.12599/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2024.

## Built on by (most cited first, 30 of 57)

- [Attention Heads of Large Language Models: A Survey](https://mlsanity.com/paper/2409.03752/) (2024)
- [PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning](https://mlsanity.com/paper/2502.12054/) (2025)
- [From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents](https://mlsanity.com/paper/2604.20006/) (2026)
- [A Comprehensive Evaluation of Cognitive Biases in LLMs](https://mlsanity.com/paper/2410.15413/) (2024)
- [PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model](https://mlsanity.com/paper/2505.06274/) (2025)
- [ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models](https://mlsanity.com/paper/2503.22048/) (2025)
- [Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text](https://mlsanity.com/paper/2506.07001/) (2025)
- [Personalize Your LLM: Fake it then Align it](https://mlsanity.com/paper/2503.01048/) (2025)
- [Collab: Controlled Decoding using Mixture of Agents for LLM Alignment](https://mlsanity.com/paper/2503.21720/) (2025)
- [Zero-Shot Strategies for Length-Controllable Summarization](https://mlsanity.com/paper/2501.00233/) (2024)
- [Measuring and Guiding Monosemanticity](https://mlsanity.com/paper/2506.19382/) (2025)
- [ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction](https://mlsanity.com/paper/2602.20708/) (2026)
- [Re-Imagining Multimodal Instruction Tuning: A Representation View](https://mlsanity.com/paper/2503.00723/) (2025)
- [TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks](https://mlsanity.com/paper/2506.12473/) (2025)
- [LLMs for Customized Marketing Content Generation and Evaluation at Scale](https://mlsanity.com/paper/2506.17863/) (2025)
- [Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language](https://mlsanity.com/paper/2503.01539/) (2025)
- [Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.03098/) (2025)
- [Preference Learning for AI Alignment: a Causal Perspective](https://mlsanity.com/paper/2506.05967/) (2025)
- [Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation](https://mlsanity.com/paper/2510.15304/) (2025)
- [A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data](https://mlsanity.com/paper/2601.17717/) (2026)
- [Protecting Language Models Against Unauthorized Distillation through Trace Rewriting](https://mlsanity.com/paper/2602.15143/) (2026)
- [Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation](https://mlsanity.com/paper/2412.07334/) (2024)
- [MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning](https://mlsanity.com/paper/2507.07419/) (2025)
- [Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey](https://mlsanity.com/paper/2510.02384/) (2025)
- [Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs](https://mlsanity.com/paper/2506.05387/) (2025)
- [A Mixture of Linear Corrections Generates Secure Code](https://mlsanity.com/paper/2507.09508/) (2025)
- [Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing](https://mlsanity.com/paper/2502.02153/) (2025)
- [Evaluating Style-Personalized Text Generation: Challenges and Directions](https://mlsanity.com/paper/2508.06374/) (2025)
- [Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization](https://mlsanity.com/paper/2508.08550/) (2025)
- [Composer Vector: Style-steering Symbolic Music Generation in a Latent Space](https://mlsanity.com/paper/2604.03333/) (2026)

## Abstract (arXiv)

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.