English
Related papers

Related papers: Over-Alignment vs Over-Fitting: The Role of Featur…

200 papers

Machine learning (ML) models have difficulty generalizing when the number of training class instances are numerically imbalanced. The problem of generalization in the face of data imbalance has largely been attributed to the lack of…

Machine Learning · Computer Science 2024-07-16 Damien A. Dablain , Nitesh V. Chawla

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Computation and Language · Computer Science 2025-10-31 Yuto Harada , Yusuke Yamauchi , Yusuke Oda , Yohei Oseki , Yusuke Miyao , Yu Takagi

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

Neural collapse (NC) is a phenomenon that emerges at the terminal phase of the training (TPT) of deep neural networks (DNNs). The features of the data in the same class collapse to their respective sample means and the sample means exhibit…

Machine Learning · Statistics 2024-09-09 Wanli Hong , Shuyang Ling

Large language models (LLMs) have exhibited impressive performance and surprising emergent properties. However, their effectiveness remains limited by the fixed context window of the transformer architecture, posing challenges for…

Computation and Language · Computer Science 2025-06-16 Tianqi Du , Haotian Huang , Yifei Wang , Yisen Wang

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to explain this effect, most theoretical insights are limited to…

Machine Learning · Computer Science 2025-10-30 Junsoo Oh , Jerry Song , Chulhee Yun

It is generally believed that robust training of extremely large networks is critical to their success in real-world applications. However, when taken to the extreme, methods that promote robustness can hurt the model's sensitivity to rare…

Machine Learning · Computer Science 2021-05-21 Seungyeon Kim , Daniel Glasner , Srikumar Ramalingam , Cho-Jui Hsieh , Kishore Papineni , Sanjiv Kumar

Federated Learning (FL) on graphs enables collaborative model training to enhance performance without compromising the privacy of each client. However, existing methods often overlook the mutable nature of graph data, which frequently…

Machine Learning · Computer Science 2025-03-07 Sungwon Kim , Yoonho Lee , Yunhak Oh , Namkyeong Lee , Sukwon Yun , Junseok Lee , Sein Kim , Carl Yang , Chanyoung Park

The push to train ever larger neural networks has motivated the study of initialization and training at large network width. A key challenge is to scale training so that a network's internal representations evolve nontrivially at all…

Machine Learning · Computer Science 2024-05-15 Greg Yang , James B. Simon , Jeremy Bernstein

Superalignment, where humans act as weak supervisors for superhuman models, has become a crucial problem with the rapid development of Large Language Models (LLMs). Recent work has preliminarily studied this problem by using weak models to…

Computation and Language · Computer Science 2025-03-03 Wenkai Yang , Shiqi Shen , Guangyao Shen , Wei Yao , Yong Liu , Zhi Gong , Yankai Lin , Ji-Rong Wen

We consider the problem of generalization of arbitrarily overparameterized two-layer ReLU Neural Networks with univariate input. Recent work showed that under square loss, flat solutions (motivated by flat / stable minima and Edge of…

Machine Learning · Computer Science 2025-12-02 Dan Qiao , Yu-Xiang Wang

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

Pre-training is prevalent in nowadays deep learning to improve the learned model's performance. However, in the literature on federated learning (FL), neural networks are mostly initialized with random weights. These attract our interest in…

Machine Learning · Computer Science 2023-03-24 Hong-You Chen , Cheng-Hao Tu , Ziwei Li , Han-Wei Shen , Wei-Lun Chao

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge.…

Machine Learning · Computer Science 2020-04-02 Zhi Han , Siquan Yu , Shao-Bo Lin , Ding-Xuan Zhou

It remains a puzzle that why deep neural networks (DNNs), with more parameters than samples, often generalize well. An attempt of understanding this puzzle is to discover implicit biases underlying the training process of DNNs, such as the…

Machine Learning · Computer Science 2019-05-27 Yaoyu Zhang , Zhi-Qin John Xu , Tao Luo , Zheng Ma

Few-Shot Learning (FSL) algorithms are commonly trained through Meta-Learning (ML), which exposes models to batches of tasks sampled from a meta-dataset to mimic tasks seen during evaluation. However, the standard training procedures…

Machine Learning · Computer Science 2024-10-28 Mateusz Ochal , Massimiliano Patacchiola , Amos Storkey , Jose Vazquez , Sen Wang

Adversarial training is widely used to improve the robustness of deep neural networks to adversarial attack. However, adversarial training is prone to overfitting, and the cause is far from clear. This work sheds light on the mechanisms…

Machine Learning · Computer Science 2022-12-12 Lin Li , Michael Spratling

Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the…

Artificial Intelligence · Computer Science 2026-05-05 Gouki Minegishi , Hiroki Furuta , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo

The infrequent occurrence of overfit in deep neural networks is perplexing. On the one hand, theory predicts that as models get larger they should eventually become too specialized for a specific training set, with ensuing decrease in…

Machine Learning · Computer Science 2023-12-29 Uri Stern , Daphna Weinshall

In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Mamshad Nayeem Rizve , Salman Khan , Fahad Shahbaz Khan , Mubarak Shah