Controllable Text Generation

Ask about this topic

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

109 papers5 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

  1. HiFlow: Hierarchical Feedback-Driven Optimization for Constrained Long-Form Text Generation

    Mar 5, 2026Yifan Zhu, Guanting Chen, Bing Wei +1Text GenerationConstrained Generative Modeling

    Beijing University of Posts and Telecommunications · Hainan University · Nanyang Technological University

  2. QCAgent: An agentic framework for quality-controllable pathology report generation from whole slide image

    Mar 2, 2026Rundong Wang, Wei Ba, Ying Zhou +8Medical Report GenerationComputational Pathology

    School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230026, P.R. China · Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advance Research, USTC, 215123, P.R. China · Chinese PLA General Hospital Ninth Medical Center, China +1

  3. Suffix-Constrained Greedy Search Algorithms for Causal Language Models

    Mar 1, 2026Ayoub Hammal, Pierre Zweigenbaum, Caio CorroConstrained Generative ModelingConstrained Decoding

    1Université Paris-Saclay, CNRS, LISN · 2INSA Rennes, IRISA, CNRS, Université de Rennes

  4. Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection

    Feb 26, 2026Keito InoshitaMulti-Agent LLM SystemsControllable Text Generation

    Faculty of Business and Commerce, Kansai University, Suita, Japan

  5. IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages

    Feb 25, 2026Thanmay Jayakumar, Mohammed Safi Ur Rahman Khan, Raj Dabre +2Instruction FollowingMultilingual Language Model Evaluation

    Nilekani Centre at AI4Bharat · Indian Institute of Technology Madras, India · IT University of Copenhagen +1

  6. Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning

    Feb 24, 2026Justin Lovelace, Christian Belardi, Sofian Zalouk +3Autoregressive Language ModelingDiffusion Language Models

    Department of Computer Science, Cornell University

  7. PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra

    Feb 17, 2026Xiachong Feng, Liang Zhao, Weihong Zhong +5Controllable Text GenerationPersonality Modeling in Language Models

    Harbin Institute of Technology · The University of Hong Kong

  8. Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities

    Jan 29, 2026Tien Dang, The-Hai Nguyen, Dinh Mai Phuong +5Linear Representation HypothesisControllable Text Generation

    Japan Advanced Institute of Science and Technology · Monash University · Quantum AI and Cyber Security Institute, FPT Corporation +1

  9. ILRR: Inference-Time Steering Method for Masked Diffusion Language Models

    Jan 29, 2026Eden Avrahami, Eliya NachmaniMasked Diffusion ModelsLanguage Model Steering

    School of Computer Science, Tel Aviv University, Israel · Department of Electrical and Computer Engineering, Ben Gurion University, Beer Sheva, Israel.

  10. Steering Language Models Before They Speak: Logit-Level Interventions

    Jan 16, 2026Hyeseon An, Shinwoo Park, Hyundong Jin +1Language Model SteeringControllable Text Generation

    Department of Computer Science, Yonsei University, Seoul, South Korea

  11. Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

    Jan 10, 2026Yutong Song, Jiang Wu, Shaofan Yuan +5LLM PersonalizationControllable Text Generation

    University of California, Irvine · Independent Researcher · TikTok

  12. Edit Policy-Aligned Text Simplification

    Dec 6, 2025Xuanxin Wu, Yuki Arase, Masaaki NagataText SimplificationControllable Text Generation

    The University of Osaka · Institute of Science Tokyo · NTT Inc.

  13. Metamodel-Guided Model Generation with Layered Constraints

    Oct 29, 2025Tong Ma, Hui Lai, Hui Wang +4Software EngineeringControllable Text Generation

    University of Science and Technology of China, China · Hefei Institutes of Physical Science, Chinese Academy of Sciences, China · Anhui University, China

  14. Scaling Personality Control in LLMs with Big Five Scaler Prompts

    Aug 8, 2025Gunhee Cho, Yun-Gyung CheongPersona-Conditioned GenerationControllable Text Generation

    Sungkyunkwan University, South Korea

  15. LaViDa: A Large Diffusion Language Model for Multimodal Understanding

    May 22, 2025Shufan Li, Konstantinos Kallidromitis, Hritik Bansal +7Multimodal UnderstandingVision-Language Models

    1UCLA · 2Panasonic AI Research · 4Salesforce Research +1

  16. LDC: Learning to Generate Research Idea with Dynamic Control

    Dec 19, 2024Ruochen Li, Liqiang Jing, Chi Han +2Controllable Text GenerationResearch Idea Generation

    University of Texas at Dallas · UIUC · Stony Brook University

  17. PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction

    Dec 4, 2024Junhong Liang, Bojun ZhangControllable Text GenerationAutomatic Speech Recognition

    Mohamed bin Zayed University of Artificial Intelligence · Institute of Automation, Chinese Academy of Sciences

  18. LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

    Jun 30, 2024Hye Ryung Son, Saehee Eom, Mooho Song +1Controllable Text GenerationLLM Safety

    Graduate School of Data Science Seoul National University · Georgia Institute of Technology

  19. LiSeCo: Linear Semantic Control for Language Generation

    May 24, 2024Emily Cheng, Carmen Amo AlonsoLanguage Model SteeringControllable Text Generation

    Universitat Pompeu Fabra, Barcelona, Spain · Stanford University, CA, USA

  20. Controlled Text Generation via Language Model Arithmetic

    Nov 24, 2023Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner +1Controllable Text Generation

    Department of Computer Science, ETH Zurich, Switzerland