Text Generation

Follow this topic Ask about this topic

Momentum

33 papers in the last four weeks, up 175% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 265

All topics

When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis
Apr 17, 2026Justice Owusu Agyemang, Michael Agyare, Miriam Kobbinah +2LLM Inference Efficiency Long-Form Document Generation
Sperix Labs · GCTU, Ghana · NCA, Ghana +1
The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings
Apr 16, 2026Hengky Susanto, David James Woo, Chingyi Yeung +2AI in Education Text Generation
Education University of Hong Kong, Hong Kong, China · Everwrite Limited, Hong Kong, China · International Christian School, Hong Kong, China
Schema-Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding
Apr 16, 2026Yifan LeConstrained Generative Modeling Constrained Decoding
Independent Researcher
Acceptance Dynamics Across Cognitive Domains in Speculative Decoding
Apr 16, 2026Seifeldin AbdellatifSpeculative Decoding Text Generation
College of Engineering, Al Ain University Abu Dhabi, United Arab Emirates
Bridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specifications
Apr 8, 2026Sneha Gathani, Sirui Zeng, Diya Patel +5LLM Code Generation Text Generation
University of Maryland, College Park College Park, Maryland, USA · Adobe Research San Jose, California, USA · Microsoft Research Seattle, Washington, USA +2
AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing
Mar 24, 2026Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan +1Text Generation
Department of Language Science and Technology, Saarland Informatics Campus Saarland University, Saarbrücken, Germany
Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation
Mar 16, 2026Yanick Zengaffinen, Andreas Opedal, Donya Rooein +3LLM Prompting Generative AI in Education
1ETH Zürich · 2Bocconi University · University of Central Florida
Language Generation with Replay: A Learning-Theoretic View of Model Collapse
Mar 12, 2026Giorgio Racca, Michal Valko, Amartya SanyalModel Collapse Data Contamination in Language Models
University of Copenhagen · Isara Labs
CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation
Feb 13, 2026Yiran Rex Ma, Yuxiao Ye, Huiyuan XieAutomated Evaluation Legal NLP
School of Foreign Languages, Peking University · Department of Computer Science and Technology, Tsinghua University
CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
Feb 4, 2026Zhao Tong, Chunlin Gong, Yiping Zhang +5Language Model Safety Evaluation LLM Interpretability
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · Shanghai AI Laboratory +3
Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance
Jan 20, 2026Qianli Ma, Chang Guo, Zhiheng Tian +4Multi-Agent LLM Systems LLM Hallucination Mitigation
AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University
STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models
Jan 19, 2026Xiangyu Shi, Junyang Ding, Xu Zhao +8Text-to-CAD Generation Text Generation
Northwestern University, Evanston, USA
Safe Language Generation in the Limit
Jan 13, 2026Antonios Anastasopoulos, Giuseppe Ateniese, Evgenios M. KornaropoulosLanguage Identification Text Generation
Department of Computer Science George Mason University
DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation
Dec 19, 2025Janghoon Han, Heegyu Kim, Changho Lee +6Deep Research Agents LLM Agent Evaluation
LG AI Research · University of Illinois Chicago · University of Michigan, Ann Arbor
Tell Me: An LLM-powered Mental Well-being Assistant with RAG, Synthetic Dialogue Generation, and Agentic Planning
Nov 18, 2025Trishala Jayesh AhalparaMental Health Counseling Mental Health
Fujitsu Research of America Santa Clara, USA
MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
Sep 30, 2025Mingjin Li, Yu Liu, Huayi Liu +4Multi-Agent LLM Systems Synthetic Data Generation
Baidu Inc., Beijing, China
Generating Individual Travel Diaries Using Large Language Models Informed by Census and Land-Use Data
Sep 7, 2025Sepehr Golrokh Amin, Devin Rhoads, Fatemeh Fakhrmoosavi +2Synthetic Data Generation Synthetic Data Evaluation
School of Civil and Environmental Engineering, University of Connecticut, United States
MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions
Sep 4, 2025Aishik Mandal, Tanmoy Chakraborty, Iryna GurevychMental Health Counseling Mental Health
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technische Universität Darmstadt · National Research Center for Applied Cybersecurity ATHENE, Germany · Department of Electrical Engineering, Indian Institute of Technology Delhi, India +1
BOW: Training Language Models to Reason Over Plausible Next Words
Jun 16, 2025Ming Shen, Zhikun Xu, Jacob Dineen +2RL for Language Model Reasoning Next-Token Prediction
Arizona State University
Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques
May 31, 2025Raina Gao, Alyssa Jeong, Lang Xiong +4LLM Evaluation Text Generation
Algoverse AI Research
DLM-One: Diffusion Language Models for One-Step Sequence Generation
May 30, 2025Tianqi Chen, Shujian Zhang, Mingyuan ZhouDiffusion Language Models Diffusion Model Distillation
The University of Texas at Austin, Austin, TX 78712, USA
Ensemble Learning for Large Language Models in Text and Code Generation: A Survey
Mar 13, 2025Mari Ashiga, Wei Jie, Fan Wu +5Mixture-of-Experts Language Models Language Model Ensembles
School of Computing and Engineering, University of West London, London W5 5RF, United Kingdom · Turing Intelligence Technology Limited, London EC2M 2PF, United Kingdom · School of Computer Science, University of Leeds, Leeds LS2 9JT, United Kingdom
Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias
Feb 14, 2025Enzo Doyen, Amalia TodirascuGender Bias in Language Models Language Model Bias Evaluation
University of Strasbourg
LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization
Jun 30, 2024Hye Ryung Son, Saehee Eom, Mooho Song +1Controllable Text Generation LLM Safety
Graduate School of Data Science Seoul National University · Georgia Institute of Technology
Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor
Jul 31, 2022Caleb Princewill NwokochaInterpretable ML Incremental Learning

Apr 17, 2026, cs.AIJ/K move · Enter open · S save

When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis

Justice Owusu Agyemang, Michael Agyare, Miriam Kobbinah, Nathaniel Agbugblah+1

Sperix Labs · GCTU, Ghana · NCA, Ghana+1

LLM Inference Efficiency Long-Form Document Generation Structured Output Generation Text Generation LLM Agent Reliability

Open paper AskPDF arXiv

LLM-powered coding agents suffer from a poorly understood failure mode we term output stalling: the agent silently produces empty responses when attempting to generate large, format-heavy documents. We present a theoretical framework that explains and prevents this failure through three contributions. (1) We introduce Output Generation Capacity (OGC), a formal measure of an agent's effective ability to produce output given its current context state - distinct from and empirically smaller than the raw context window. (2) We prove a Format-Cost Separation Theorem showing that deferred template rendering is always at least as token-efficient as direct generation for any format with overhead multiplier

μ_f > 1

, and derive tight bounds on the savings. (3) We formalize Adaptive Strategy Selection, a decision framework that maps the ratio of estimated output cost to available OGC into an optimal generation strategy (direct, chunked, or deferred). We validate the theory through controlled experiments across three models (Claude 3.5 Sonnet, GPT-4o, Llama 3.1 70B), four document types, and an ablation study isolating each component's contribution. Deferred rendering reduces LLM generation tokens by 48-72% across all conditions and eliminates output stalling entirely. We instantiate the framework as GEN-PILOT, an open-source MCP server, demonstrating that the theory translates directly into a practical tool.

Momentum

Related topics

Latest papers 265