# Controlled Text Generation with Natural Language Instructions

arXiv: https://arxiv.org/abs/2304.14293 · HTML: https://mlsanity.com/paper/2304.14293/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 60 references that are in the map.
- First posted on arXiv 27 Apr 2023.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)

## Built on by (most cited first, 30 of 87)

- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023)
- [Can Large Language Models Understand Real-World Complex Instructions?](https://mlsanity.com/paper/2309.09150/) (2023)
- [Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization](https://mlsanity.com/paper/2311.09184/) (2023)
- [CFBench: A Comprehensive Constraints-Following Benchmark for LLMs](https://mlsanity.com/paper/2408.01122/) (2024)
- [TrustAgent: Towards Safe and Trustworthy LLM-based Agents](https://mlsanity.com/paper/2402.01586/) (2024)
- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [Prompt Engineering a Prompt Engineer](https://mlsanity.com/paper/2311.05661/) (2023)
- [PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs](https://mlsanity.com/paper/2305.12392/) (2023)
- [MM-IFEngine: Towards Multimodal Instruction Following](https://mlsanity.com/paper/2504.07957/) (2025)
- [LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints](https://mlsanity.com/paper/2410.06458/) (2024)
- [Suri: Multi-constraint Instruction Following for Long-form Text Generation](https://mlsanity.com/paper/2406.19371/) (2024)
- [Benchmarking Large Language Models on Controllable Generation under Diversified Instructions](https://mlsanity.com/paper/2401.00690/) (2024)
- [Weaver: Foundation Models for Creative Writing](https://mlsanity.com/paper/2401.17268/) (2024)
- [From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models](https://mlsanity.com/paper/2404.15846/) (2024)
- [Mathematical Language Models: A Survey](https://mlsanity.com/paper/2312.07622/) (2023)
- [The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models](https://mlsanity.com/paper/2406.19999/) (2024)
- [Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text](https://mlsanity.com/paper/2506.07001/) (2025)
- [Automating Steering for Safe Multimodal Large Language Models](https://mlsanity.com/paper/2507.13255/) (2025)
- [Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs](https://mlsanity.com/paper/2402.11218/) (2024)
- [Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation](https://mlsanity.com/paper/2405.03085/) (2024)
- [PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners](https://mlsanity.com/paper/2310.02469/) (2023)
- [GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence](https://mlsanity.com/paper/2310.05388/) (2023)
- [Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF](https://mlsanity.com/paper/2403.10088/) (2024)
- [Self-Steering Language Models](https://mlsanity.com/paper/2504.07081/) (2025)
- [A Survey of Controllable Learning: Methods and Applications in Information Retrieval](https://mlsanity.com/paper/2407.06083/) (2024)
- [A Survey on Mathematical Reasoning and Optimization with Large Language Models](https://mlsanity.com/paper/2503.17726/) (2025)
- [KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval](https://mlsanity.com/paper/2310.15511/) (2023)

## Abstract (arXiv)

Large language models generate fluent texts and can follow natural language instructions to solve a wide range of tasks without task-specific training. Nevertheless, it is notoriously difficult to control their generation to satisfy the various constraints required by different applications. In this work, we present InstructCTG, a controlled text generation framework that incorporates different constraints by conditioning on natural language descriptions and demonstrations of the constraints. In particular, we first extract the underlying constraints of natural texts through a combination of off-the-shelf NLP tools and simple heuristics. We then verbalize the constraints into natural language instructions to form weakly supervised training data. By prepending natural language descriptions of the constraints and a few demonstrations, we fine-tune a pre-trained language model to incorporate various types of constraints. Compared to existing search-based or score-based methods, InstructCTG is more flexible to different constraint types and has a much smaller impact on the generation quality and speed because it does not modify the decoding procedure. Additionally, InstructCTG allows the model to adapt to new constraints without re-training through the use of few-shot task generalization and in-context learning abilities of instruction-tuned language models.