mlsanityData to 7 Oct 2026

Controlled Text Generation with Natural Language Instructions

arXiv 2304.14293 ↗First posted 27 Apr 2023cs.CL cs.AI cs.LGcited by 87

Not on the map. Why?

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.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Builds on 44 of its 60 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

44 of 60 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  9. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  12. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
32 more
  1. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  2. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  3. 2018Hierarchical Neural Story Generationcited by 1,182
  4. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  5. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  6. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  7. 2021MetaICL: Learning to Learn In Contextcited by 450
  8. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  9. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  10. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
  11. 2018Constituency Parsing with a Self-Attentive Encodercited by 196
  12. 2021Generating Datasets with Pretrained Language Modelscited by 192
  13. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  14. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  15. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  16. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  17. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  18. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  19. 2021Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collectionscited by 128
  20. 2022Locally Typical Samplingcited by 108
  21. 2016Guided Open Vocabulary Image Captioning with Constrained Beam Searchcited by 105
  22. 2019Automatically Neutralizing Subjective Bias in Textcited by 105
  23. 2020Politeness Transfer: A Tag and Generate Approachcited by 78
  24. 2019Training Neural Machine Translation To Apply Terminology Constraintscited by 73
  25. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64
  26. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  27. 2018Harvesting Paragraph-Level Question-Answer Pairs from Wikipediacited by 49
  28. 2020Pre-training Text-to-Text Transformers for Concept-centric Common Sensecited by 42
  29. 2022M2D2: A Massively Multi-domain Language Modeling Datasetcited by 26
  30. 2019Improving Grammatical Error Correction with Machine Translation Pairscited by 17
  31. 2020Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redactioncited by 17
  32. 2021Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generationcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 18; 2024: 37; 2025: 25; 2026: 7.

87 papers.

Sort:

By area:

  1. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilitycited by 162
  2. 2024Improving Instruction-Following in Language Models through Activation Steeringcited by 149
  3. 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
  4. 2023Word Embeddings Are Steers for Language Modelscited by 70
  5. 2023Can Large Language Models Understand Real-World Complex Instructions?cited by 69
  6. 2023Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarizationcited by 69
  7. 2024CFBench: A Comprehensive Constraints-Following Benchmark for LLMscited by 65
  8. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 62
  9. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  10. 2023Prompt Engineering a Prompt Engineercited by 53
  11. 2023PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMscited by 44
  12. 2025MM-IFEngine: Towards Multimodal Instruction Followingcited by 41
38 more
  1. 2024Suri: Multi-constraint Instruction Following for Long-form Text Generationcited by 34
  2. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraintscited by 34
  3. 2024From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Modelscited by 27
  4. 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructionscited by 26
  5. 2024Weaver: Foundation Models for Creative Writingcited by 25
  6. 2023Mathematical Language Models: A Surveycited by 24
  7. 2024The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Modelscited by 18
  8. 2025Automating Steering for Safe Multimodal Large Language Modelscited by 17
  9. 2024Controlled Text Generation for Large Language Model with Dynamic Attribute Graphscited by 16
  10. 2024Compressing Long Context for Enhancing RAG with AMR-based Concept Distillationcited by 16
  11. 2025Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Textcited by 16
  12. 2023GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidencecited by 14
  13. 2023PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learnerscited by 13
  14. 2024Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIFcited by 13
  15. 2025Self-Steering Language Modelscited by 13
  16. 2024A Survey of Controllable Learning: Methods and Applications in Information Retrievalcited by 12
  17. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Modelscited by 12
  18. 2024LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexiconscited by 11
  19. 2024KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questionscited by 11
  20. 2023KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrievalcited by 10
  21. 2024CoDa: Constrained Generation based Data Augmentation for Low-Resource NLPcited by 9
  22. 2024PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awarenesscited by 9
  23. 2025ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructionscited by 9
  24. 2024MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmarkcited by 8
  25. 2024Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Taskscited by 8
  26. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  27. 2024Standardize: Aligning Language Models with Expert-Defined Standards for Content Generationcited by 7
  28. 2024A Survey of Automatic Hallucination Evaluation on Natural Language Generationcited by 7
  29. 2024Controllable Text Generation in the Instruction-Tuning Eracited by 7
  30. 2023PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generationcited by 6
  31. 2024Aligning Large Language Models with Diverse Political Viewpointscited by 6
  32. 2025Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generationcited by 6
  33. 2024Analysis of Plan-based Retrieval for Grounded Text Generationcited by 5
  34. 2024Control Large Language Models via Divide and Conquercited by 5
  35. 2025Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliancecited by 5
  36. 2025Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotationcited by 5
  37. 2023Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understandingcited by 4
  38. 2023Psychometric Predictive Power of Large Language Modelscited by 4

50 most cited of 87 All 87 (JSON)