LLM Training

LLM: Large Language Model

Large language model training studies how models acquire language and task abilities, from large-scale next-token pretraining to supervised fine-tuning and preference or reinforcement learning. Common approaches combine data curation, filtering and mixture design with curricula, scaling laws, and optimization methods such as AdamW and matrix-based optimizers. Systems research makes training more practical through low-precision arithmetic, memory-efficient methods, and distributed parallelism, while domain adaptation and synthetic reasoning data target specific capabilities. A central tension is how to improve generalization and reliability while controlling compute and data costs, avoiding memorization and instability, and measuring gains beyond benchmark scores.

Latest papers

353 papers62 papers in the last four weeks, up 94% on the four weeks before. 0.4% of all new papers.

Training Foundation Models with a Single Algorithm
Oct 29, 2026Yuda Song, Alvin Zhang, Fahim Tajwar +7LLM Training RL for Language Models
Carnegie Mellon University · Johns Hopkins University · Aurora Innovation
Deeper Backpropagation or More Updates? Training Looped Language Models Across Budgets
Oct 28, 2026Jiarun Shen, Xiao LiLLM Training Efficient Language Model Training
The Chinese University of Hong Kong, Shenzhen
The Role of Quantization in Loss Spikes
Oct 28, 2026Zaiqian Chen, Aditya Somasundaram, Sophie Li +4LLM Training Language Model Pretraining
Columbia University · Mohamed bin Zayed University of Artificial Intelligence · University of Maryland +1
Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and Training
Oct 28, 2026Ulyana Tkachenko, Hui Wen Goh, Guram Gogia +1Automatic Rubric Generation Rubric-Based Evaluation
Handshake AI
Think Twice: The Metis-1.6 Technical Report
Oct 27, 2026Giulianno VollmerLLM Training Efficient Language Model Training
Lernex Research
Locating Sycophancy Across Training Stages in Open Language Models
Oct 27, 2026Jiarui Yao, Shweta Parihar, Nghia Tuan Bui +2LLM Sycophancy LLM Training
Boston Children’s Hospital and Harvard Medical School · New Jersey Institute of Technology
Advancement or Acceleration? How Data Curation Improves LLM Training
Oct 27, 2026Jiaxing Wang, Zicheng Zhang, Deping Xiang +5Training Data Curation LLM Training
University of Oxford
Specialization, Diversity, and Scaling in Child-Scale Language Models
Oct 27, 2026Steven Y. Feng, Michael C. FrankSmall Language Models LLM Training
Stanford University
Large Language Models: A Plain-Language Overview for Engineers
Oct 25, 2026Bahaeddin TürkoğluLLM Training LLM Prompting
Department of Artificial Intelligence and Data Engineering, Ankara University, Ankara, Türkiye
Transformer to GPT-5: Advancements, Limitations, and Future Directions in Large Language Model Design
Oct 25, 2026Harsidak Singh Banwait, Chander PrabhaLanguage Model Scaling LLM Training
Chitkara University of Engineering and Technology, Chitkara University, Punjab, India
Software Engineering LLMs: Why We Need Them and How Software Engineering Helps Build Them
Oct 24, 2026Amir M. Ebrahimi, Mohammed Mehedi Hasan, Seyed Shayan Daneshvar +3Code Language Models LLM Training
Queen’s University, Canada · University of Manitoba, Canada · Center for Software Excellence, Huawei Technologies, Canada
A Distribution-Matching Perspective on LLM Training Algorithms
Oct 24, 2026Yanxing Huang, Bingzhang Yan, Zihan Tang +3LLM Training Language Model Distillation
Qiuzhen College, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Weiyang College, Tsinghua University, Beijing, China +2
A Comprehensive Framework for All Stages of Large-Model Training: From Data and Tokenization, through Pretraining, to Post-Training Alignment
Oct 24, 2026Xiangjing An, Zhibin Jiao, Aiting ChenLLM Training Language Model Post-Training
Independent Researcher Team
Data Optimization for LLMs: A Survey
Oct 24, 2026Ou WuLLM Training Large Language Model-Based Data Augmentation
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, China
Training an MoE LLM in MXFP4: How We Closed the Gap to BF16
Oct 23, 2026Han Wang, Zhitao Wang, Natalia Frumkin +4LLM Quantization Low-Precision Training
Advanced Micro Devices, Inc.
Democratizing LLM Training with the Edge: Challenges, Systems, and the Road Ahead
Oct 23, 2026Ziyue Luo, Jiaxuan Cai, Cedric LeDenmat +27LLM Training Distributed Training
The Ohio State University · University of Wisconsin–Madison · Rochester Institute of Technology +5
PRISM: Promoting Sampling Diversity of Large Language Models with Implicit Stochastic Modulation
Oct 23, 2026Qixin Xu, Zihan Zhu, Xiaojiang Liu +1Output Diversity in Language Models LLM Training
Tsinghua University. · Apple.
Data Schedules and Learning Rate Schedules Should Be Designed Together
Oct 21, 2026Haodong Wen, Kairong Luo, Tingkai Yan +2LLM Training Continued Pretraining
Tsinghua University · Peng Cheng Laboratory
Africa-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language Models
Oct 20, 2026Mich-Seth OwusuLanguage Model Pretraining LLM Training
AfriSpeech
MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language Models
Oct 19, 2026Zhengao Li, Chuxu Zhang, Yushun DongKnowledge Augmentation for Language Models LLM Training
University of Connecticut, Storrs, CT, USA · Florida State University, Tallahassee, FL, USA
Which Long Documents Matter? A Controlled Study of Data Selection for Context Extension
Oct 17, 2026Junlong Jia, Jiang Zhou, Xing Wu +3Training Data Selection Long-Context Language Modeling
Hunyuan Team, Tencent
Ori: Drift-Aware Streaming $k$ -PCA for Very Low-Rank LLM Training
Oct 16, 2026Xinyu Luo, Jincheng Zhou, Mengbo Wang +5LLM Training Low-Rank Adaptation
Department of Computer Science, Purdue University. · Purdue Institute for Cancer Research, Purdue University. · Department of Comparative Pathobiology, Purdue University.
The Ephemeral Cost of Switching Optimizers Across LLM Training Stages
Oct 15, 2026Xinyu Zhao, Davis Wertheimer, Ashutosh Sharma +2LLM Training LLM Post-Training
MIT · MIT-IBM Watson AI Lab
Priming Base Models for Agentic Post-Training: An Open Midtraining Recipe
Oct 15, 2026Soumye Singhal, Joseph Jennings, Ka Shun Shum +11LLM Training LLM Post-Training
NVIDIA
Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle
Oct 15, 2026Yuanjian Xu, Jianing Hao, Tianze Sun +7LLM Training Data Mixture Optimization
The Hong Kong University of Science and Technology (Guangzhou) · Harbin Institute of Technology · OpenCSG +4
Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training
Oct 14, 2026Anshu Raina, Peyman Razaghi, Yuankai Chen +7Distributed Training LLM Training
Advanced Micro Devices, Inc.
LLM-jp-4 Technical Report
Oct 14, 2026LLM-jp, :, Chaoran Liu +16Language Modeling LLM Training
How Inner Optimizers Shape Replica Scaling
Oct 13, 2026Eugene Belilovsky, Stefan Horoi, Edouard Oyallon +1LLM Training Distributed Training
Mila · Concordia University · Université de Montréal +1
Monarch-Muon: Structure-Aware Muon for Fast and Memory-Efficient Pretraining
Oct 12, 2026Alexander Miasnikov, Ruslan Kabirov, Gleb Molodtsov +7Muon Optimizer LLM Training
BRAIn Lab · HSE University · MBZUAI
SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
Oct 12, 2026Xupeng Chen, Chenqian Le, Jiayi Cheng +2Language Model Post-Training LLM Training
New York University · University of Southern California · Columbia University

Oct 29, 2026J/K move · Enter open · S save

Training Foundation Models with a Single Algorithm

Yuda Song, Alvin Zhang, Fahim Tajwar, Daman Arora+6

Carnegie Mellon University · Johns Hopkins University · Aurora Innovation

LLM Training RL for Language Models

Open paper AskPDF arXiv

Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show that this algorithmic separation is not fundamental. By deriving suitable RL objectives as maximum-likelihood fitting to model-generated target distributions, we place all of these stages under a single likelihood-based training algorithm, unified training. This perspective turns the foundation-model training lifecycle into a problem of choosing which data to train on, in what proportions, and when, with conventional staged training as a special case. We instantiate this framework in a unified training system that mixes static data and RL generations within a single trainer. Across controlled and real-world experiments, unified training improves the accuracy-compute tradeoff and task coverage while preserving broader capabilities, and provides a stronger starting point for continual learning. This work lays the groundwork for a unified science of foundation-model training, connecting mathematical principles, training infrastructure, and the development of model capabilities.