Controllable Text Generation

Overview

Controllable text generation studies how to make generated language reliably match goals such as a requested style, sentiment, reading level, length, format, or safety condition. Approaches include prompts and control tokens, fine-tuning and preference optimization, decoding-time constraints and guidance, activation steering, and planning or feedback-based revision; some methods also control generation in diffusion models. These techniques support applications from education and creative writing to healthcare, where outputs may need to meet several requirements at once. A central challenge is balancing reliable constraint satisfaction with fluency, factuality, diversity, and user-specific preferences, while evaluating systems consistently across tasks and languages.

Latest papers

CardsList

115 papers8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

  1. Activation Steering the Nan-Shan in Typhoon

    Nov 13, 2026Megan Wei, Damon Pham, John Cayley +1Controllable Text GenerationLanguage Model Steering

  2. VWEN: A Curated Small Language Model for Vietnamese Paraphrasing

    Nov 11, 2026Sang Quang NguyenLanguage Model Post-TrainingText Generation

  3. Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition

    Oct 31, 2026Alejandro Mozo Quesada, Sergio Gálvez Rojas, Francisco López ValverdeRepetition in Language GenerationControllable Text Generation

  4. Nedimo: An Evidence-Grounded Multilingual Pipeline for AI-Generated Sleep Stories

    Oct 29, 2026Georgios Makridis, Stefanos KampourisAudio GenerationNarrative Generation

  5. Grammar Control for Language Learning with Sequential Monte Carlo and Small Language Models

    Oct 29, 2026Kate McCurdy, Jacob Hoover Vigly, Thomas Hikaru Clark +6Controllable Text GenerationSmall Language Models

  6. Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance

    Oct 26, 2026Ngoc Trinh Hung Nguyen, Alonso Silva, Armen Aghasaryan +1Constrained DecodingConstraint-Guided Reasoning in Language Models

  7. From Black Box to Controller: Inference-Time Steering of LLM via Feature Amplification

    Oct 19, 2026Keqi Chen, Zekai Sun, Yuhua Wen +5Language Model SteeringControllable Text Generation

  8. AMEND: Constraint-Guided Multi-Agent Text Detoxification with Isolated Critics

    Oct 16, 2026Tianyu WangText DetoxificationControllable Text Generation

  9. Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning

    Oct 7, 2026Ahmad Abbas, Tamara Fakih, Nour Fakih +1Controllable Text GenerationArabic NLP

  10. One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation

    Sep 27, 2026Nafis Irtiza Tripto, Delvin Ce Zhang, Mahjabin Nahar +1LLM EvaluationControllable Text Generation

  11. Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs

    Sep 23, 2026Haitong Jiang, Chunlin Liu, Yile Wang +1LLM Self-CorrectionControllable Text Generation

  12. Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech

    Sep 15, 2026Greta Damo, Elias Urios Alacreu, Elena Cabrio +2Controllable Text GenerationPrompt Engineering

  13. Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study

    Sep 10, 2026Álvaro Rey-Blanes, Francisco J. Moreno-Barea, Francisco J. VeredasLLM-Assisted AnnotationControllable Text Generation

  14. SWIM: Student Writing Simulation via Proficiency-Conditioned Generation

    Sep 2, 2026Heejin Do, Jakub Kontak, Mrinmaya SachanControllable Text GenerationSynthetic Data Generation for Language Models

  15. HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks

    Sep 2, 2026Jongkyung Shin, Minguk Jeon, Chanwoo Park +1Controllable Text Generation

  16. PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation

    Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaText GenerationControllable Text Generation

  17. Beyond Surface Alignment: Grounding the Dynamics of Situational Understanding and Generative Control in LLMs

    Aug 30, 2026Chenghao YangContext EngineeringLLM Grounding

  18. Controllable Affective Generation via Latent Vector Steering

    Aug 26, 2026Xixian Yong, Siyuan Chang, Yingying Zhang +2Controllable Text GenerationActivation Steering

  19. SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

    Aug 25, 2026Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios +2Controllable Text GenerationNon-Autoregressive Text Generation

  20. Mechanistic Circuit Identification for Controllable Data Generation

    Aug 25, 2026Nakyung Lee, Sangwoo Hong, Jungwoo LeeSynthetic Data Generation for Language ModelsControllable Text Generation

  21. Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement

    Aug 24, 2026Yufeng Han, Lifan Deng, Cunliang Kong +5Human-AI Co-CreationText Generation

  22. SPOC-SQL: Stage-wise Preference Optimization for Controllable Text-to-SQL

    Aug 24, 2026Yingnan Chen, Chun Ding, Tianshi Xu +2Text-to-SQLControllable Text Generation

  23. Agentic Governance and Adversarial Verification for Policy-Constrained LLM Healthcare Appeal Generation

    Aug 20, 2026Harshil Lodhiya, Alex McManus, Reese WalkerAI Agent GovernanceMulti-Agent LLM Systems