Text Generation

Follow this topic Ask about this topic

Text generation studies how models produce language for tasks such as dialogue, summarization, storytelling, translation, and structured reports. Autoregressive transformers generate token by token, while masked-diffusion and flow-based models explore parallel or few-step generation; decoding and activation steering offer ways to adjust outputs without retraining. For longer or constrained tasks, systems combine planning, retrieval, structured representations, editing, and feedback-based training such as reinforcement learning. A central challenge is balancing speed and instruction-following with factuality, diversity, cultural fit, and quality that human readers and domain experts value.

Latest papers

423 papers51 papers in the last four weeks, up 24% on the four weeks before. 0.3% of all new papers.

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
May 10, 2026Bian Sun, Kevin Zhai, Mubarak Shah +1Diffusion Language Model Decoding Diffusion Language Models
University of Central Florida
Edit-Based Refinement for Parallel Masked Diffusion Language Models
May 10, 2026Houxing Ren, Mingjie Zhan, Zimu Lu +5Masked Diffusion Models Parallel Decoding
CUHK MMLab · SenseTime Research · Shenzhen Loop Area Institute +1
Scaling Categorical Flow Maps
May 8, 2026Oscar Davis, Anastasiia Filippova, Pierre Ablin +4Language Model Scaling Flow Map Learning
Apple · University of Oxford
Inference Time Causal Probing in LLMs
May 8, 2026Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash +1Causal Interventions in Language Models Activation Steering
School of Computer and Communication Sciences, EPFL„ Lausanne, Switzerland · 2Leiden Institute of Advanced Computer Science (LIACS), Leiden University, , Leiden, The Netherlands · College of Management of Technology, EPFL, Lausanne, Switzerland
Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
May 8, 2026Jiachen Yu, Zhihao Xu, Junjie Wang +1Instruction Following Rubric-Based Evaluation
1Tsinghua University · 2Renmin University of China
Coupling Models for One-Step Discrete Generation
May 8, 2026Fred Zhangzhi Peng, Avishek Joey Bose, Anru R. Zhang +1One-Step Generative Modeling Generative Modeling
Duke University · Imperial College London · AITHYRA
Automated Clinical Report Generation for Remote Cognitive Remediation: Comparing Knowledge-Engineered Templates and LLMs in Low-Resource Settings
May 7, 2026Yongxin Zhou, Fabien Ringeval, François PortetMedical Report Generation Clinical Language Model Evaluation
Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000 Grenoble, France
SMolLM: Small Language Models Learn Small Molecular Grammar
May 7, 2026Akhil Jindal, Harang JuSmall Language Models Mechanistic Interpretability
Moku
StoryAlign: Evaluating and Training Reward Models for Story Generation
May 6, 2026Haotian Xia, Hao Peng, Yunjia Qi +4Reward Modeling Language Model Generation Evaluation
Department of Computer Science and Technology, Tsinghua University
Benchmarking Parameter-Efficient Fine-Tuning of Large Language Models for Low-Resource Tajik Text Generation with the Tajik Web Corpus
May 5, 2026Mullosharaf K. ArabovLLM Fine-Tuning Low-Resource Language Processing
Institute of Computational Mathematics and Information Technologies Kazan Federal University Kazan, Russia
PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination
May 5, 2026Qiyao Wang, Xinyi Chen, Longze Chen +4LLM Evaluation Legal Document Analysis
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Dalian University of Technology +2
Controllable Narrative Rendering for Enhanced Assisted Writing
May 5, 2026Mingzhe Lu, Yanbing Liu, Jiayue Wu +5Narrative Generation Controllable Text Generation
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · 3HiThink Research
Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms Race
May 4, 2026Andreas Maier, Moritz Zaiss, Siming BayerAI-Generated Text Detection Language Model Generation Evaluation
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Institute of Neuroradiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
May 3, 2026Weihang Su, Xuanyi Chen, Yueyue Wu +2Legal Document Analysis Agentic RAG
Tsinghua University · Beijing, China · Quan Cheng Laboratory +1
FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents
May 3, 2026Srihari Unnikrishnan, Jaskaran Singh Walia, Drishti Goel +1Text Generation
Microsoft Research · University of Illinois Urbana-Champaign · Inception
On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
May 2, 2026Zhitao He, Haolin Yang, Rui Min +2LLM Evaluation Long-Form Document Generation
Hong Kong University of Science and Technology
Escaping Mode Collapse in LLM Generation via Geometric Regulation
May 1, 2026Xin Du, Kumiko Tanaka-IshiiLanguage Model Steering Decoder-Only Language Models
Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan · Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China · Department of Computer Science and Engineering, Waseda University, Tokyo, Japan
Consistent Diffusion Language Models
Apr 30, 2026Hasan Amin, Yuan Gao, Yaser Souri +4Few-Step Diffusion Sampling Diffusion Model Acceleration
Department of Computer Science, Purdue University · Microsoft
StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer
Apr 30, 2026Guantian ZhengFlow Matching AI-Generated Text Detection
Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues
Apr 30, 2026Muhammad Dehan Al Kautsar, Saeed Almheiri, Momina Ahsan +13Low-Resource Language Processing Arabic NLP
Mohamed bin Zayed University of Artificial Intelligence · IBM Research AI · American University in the Emirates
Instruction-Guided Poetry Generation in Arabic and Its Dialects
Apr 30, 2026Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy +5Arabic NLP Controllable Text Generation
Mohamed bin Zayed University of Artificial Intelligence
Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models
Apr 30, 2026Xiaomeng Wang, Martha Larson, Zhengyu ZhaoVLM Evaluation Vision-Language Models
Radboud University · Nijmegen, Netherlands · Xi’an Jiaotong University +1
SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling
Apr 29, 2026Eliya Naomi Aharon, Meytal Grimland, Avi Segal +4Mental Health Counseling Mental Health
Ben-Gurion University of the Negev Beer Sheva, Israel · University of Haifa Haifa, Israel · Sahar Tel Aviv, Israel
Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain
Apr 29, 2026Shang-Hsuan Chiang, Tsan-Tsung Yang, An-Zi Yen +1Grounded Text Generation Sports Analytics
National Yang Ming Chiao Tung University
From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation
Apr 28, 2026Dominik Borawski, Marta Szulc, Robert Chudy +2LLM Prompting Narrative Generation
Gda´nsk University of Technology
CARE: Counselor-Aligned Response Engine for Online Mental-Health Support
Apr 23, 2026Hagai Astrin, Ayal Swaid, Avi Segal +1Mental Health Counseling Emotional Support Conversation
Ben-Gurion University · School of Informatics, University of Edinburgh Edinburgh, UK
Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation
Apr 23, 2026Hanwen Gu, Chao Guo, Junle Wang +2LLM Planning Narrative Generation
Institute of Automation, Chinese Academy of Sciences · Tencent Turing Lab
To Know is to Construct: Schema-Constrained Generation for Agent Memory
Apr 22, 2026Lei Zheng, Weinan Song, Daili Li +1Schema-Constrained Generation Long-Term Conversational Memory
UnionPay
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
Apr 21, 2026Chengyu Huang, Sheng-Yen Chou, Zhengxin Zhang +1Self-Play RL LLM Post-Training
Department of Computer Science, Cornell University
Bangla Key2Text: Text Generation from Keywords for a Low Resource Language
Apr 21, 2026Tonmoy Talukder, G M ShahariarLow-Resource Language Processing Text Generation
1Ahsanullah University of Science and Technology · University of California - Riverside

May 10, 2026J/K move · Enter open · S save

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference

Bian Sun, Kevin Zhai, Mubarak Shah, Zhenyi Wang

University of Central Florida

Diffusion Language Model Decoding Diffusion Language Models Text Generation

Open paper AskPDF arXiv

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive models, primarily due to their ability to enable parallel decoding. Despite this advantage, most existing DLMs rely on a fixed generation length specified prior to decoding, which restricts their flexibility in real-world applications. While a few recent works attempt to support flexible-length generation, they typically suffer from notable limitations: some require costly retraining to accommodate variable-length outputs, while others depend solely on local confidence signals during decoding. Such local criteria fail to capture the evolving structure of the sequence, often resulting in suboptimal generation quality. In this paper, we propose a training-free, Bayesian structured decoding framework that formulates flexible-length generation as a dynamic structural inference problem. Our approach formulates flexible-length generation as a dynamic structural inference problem, jointly computing the expansion length, the block boundaries, and the decoding schedule. At each window expansion step, the method integrates local uncertainty with structural signals via a unified mechanism that supports dynamic structured generation, including both flexible block expansion and block organization, while maintaining coherence. Extensive experiments across multiple benchmarks demonstrate that our approach significantly improves generation quality and flexibility over existing fixed-length and flexible-length baselines. These results highlight the advantage of Bayesian structured decoding for diffusion language model, providing a principled and efficient solution for structured text generation.