English
Related papers

Related papers: Methods of improving LLM training stability

200 papers

It is generally accepted that starting neural networks training with large learning rates (LRs) improves generalization. Following a line of research devoted to understanding this effect, we conduct an empirical study in a controlled…

Machine Learning · Computer Science 2024-10-30 Ildus Sadrtdinov , Maxim Kodryan , Eduard Pokonechny , Ekaterina Lobacheva , Dmitry Vetrov

Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural heterogeneity of Transformers, potentially limiting their…

Machine Learning · Computer Science 2026-05-28 Di He , Songjun Tu , Keyu Wang , Lu Yin , Shiwei Liu

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

Machine Learning · Computer Science 2024-04-10 Georgy Tyukin

The training scale of large language models (LLMs) has reached tens of thousands of GPUs and is still continuously expanding, enabling faster learning of larger models. Accompanying the expansion of the resource scale is the prevalence of…

Q-learning is widely used algorithm in reinforcement learning community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This…

Machine Learning · Computer Science 2025-02-11 Han-Dong Lim , Donghwan Lee

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

The quantization of large language models (LLMs) has been a prominent research area aimed at enabling their lightweight deployment in practice. Existing research about LLM's quantization has mainly explored the interplay between weights and…

Computation and Language · Computer Science 2025-05-16 Yifei Gao , Jie Ou , Lei Wang , Jun Cheng , Mengchu Zhou

Post-training quantization of Large Language Models (LLMs) has proven effective in reducing the memory and computational requirements for inference. In this study, we focus on a straightforward question: When aiming for a target accuracy or…

Computation and Language · Computer Science 2025-08-08 Zeyu Cao , Boyang Gu , Cheng Zhang , Pedro Gimenes , Jianqiao Lu , Jianyi Cheng , Xitong Gao , Yiren Zhao

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Machine Learning · Computer Science 2025-12-08 Mahesh Kumar Nandwana , Youngwan Lim , Joseph Liu , Alex Yang , Varun Notibala , Nishchaie Khanna

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

Large Language Models (LLMs) have emerged as a promising cornerstone for the development of natural language processing (NLP) and artificial intelligence (AI). However, ensuring the robustness of LLMs remains a critical challenge. To…

Computation and Language · Computer Science 2025-11-07 Pankaj Kumar , Subhankar Mishra

General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies…

Computation and Language · Computer Science 2025-10-13 Changjiang Gao , Zixian Huang , Jingyang Gong , Shujian Huang , Lei Li , Fei Yuan

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Stable pre-training is essential for achieving better-performing language models. However, tracking pre-training stability by calculating gradient variance at every step is impractical due to the significant computational costs. We explore…

Computation and Language · Computer Science 2024-09-13 Woojin Chung , Jiwoo Hong , Na Min An , James Thorne , Se-Young Yun

Large language models require significant computational resources for deployment, making quantization essential for practical applications. However, the main obstacle to effective quantization lies in systematic outliers in activations and…

Machine Learning · Computer Science 2025-11-25 Cuong Pham , Hoang Anh Dung , Cuong C. Nguyen , Trung Le , Gustavo Carneiro , Jianfei Cai , Thanh-Toan Do

With the advancement of large language models (LLMs), an increasing number of student models have leveraged LLMs to analyze textual artifacts generated by students to understand and evaluate their learning. These student models typically…

Computation and Language · Computer Science 2025-02-03 Jiayi Zhang

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Machine Learning · Computer Science 2025-07-23 Debangshu Banerjee , Kintan Saha , Aditya Gopalan

Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the training is often prone to instabilities, especially in…

Artificial Intelligence · Computer Science 2026-05-13 Yiming Dong , Kun Fu , Haoyu Li , Xinyuan Zhu , Yurou Liu , Lijing Shao , Jieping Ye , Zheng Wang

Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime…

Machine Learning · Computer Science 2026-04-28 Paul-Tiberiu Iordache , Elena Burceanu

We investigate the problem of learning linear quadratic regulators (LQR) in a multi-task, heterogeneous, and model-free setting. We characterize the stability and personalization guarantees of a policy gradient-based (PG) model-agnostic…

Optimization and Control · Mathematics 2024-06-04 Leonardo F. Toso , Donglin Zhan , James Anderson , Han Wang