English
Related papers

Related papers: Implicit Word Reordering with Knowledge Distillati…

200 papers

This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution holds valuable insights for the student, beyond the…

Though convolutional neural networks are widely used in different tasks, lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinder their practical application. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Yufei Wang , Haoliang Li , Lap-pui Chau , Alex C. Kot

Although large models have shown a strong capacity to solve large-scale problems in many areas including natural language and computer vision, their voluminous parameters are hard to deploy in a real-time system due to computational and…

Machine Learning · Computer Science 2025-01-07 Sirong Wu , Xi Luo , Junjie Liu , Yuhui Deng

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…

Computation and Language · Computer Science 2026-05-15 Yumeng Zhang , Zhengbang Yang , Yevin Nikhel Goonatilake , Zhuangdi Zhu

Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model. Considering the ever-growing size of pre-trained language models…

Machine Learning · Computer Science 2023-04-13 Ivan Kobyzev , Aref Jafari , Mehdi Rezagholizadeh , Tianda Li , Alan Do-Omri , Peng Lu , Pascal Poupart , Ali Ghodsi

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages. Our model only relies on the Bible, a considerably smaller parallel data…

Computation and Language · Computer Science 2019-03-15 Mohammad Sadegh Rasooli , Michael Collins

Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models. However, unauthorized use of knowledge distillation takes unfair advantage of the considerable effort…

Artificial Intelligence · Computer Science 2026-04-20 Xinhang Ma , William Yeoh , Ning Zhang , Yevgeniy Vorobeychik

Knowledge distillation is one of the most effective methods for model compression. Previous studies have focused on the student model effectively training the predictive distribution of the teacher model. However, during training, the…

Computation and Language · Computer Science 2026-01-29 Junseok Lee , Nahoon Kim , Sangyong Lee , Chang-Jae Chun

While Knowledge Distillation (KD) has been recognized as a useful tool in many visual tasks, such as supervised classification and self-supervised representation learning, the main drawback of a vanilla KD framework is its mechanism, which…

Computer Vision and Pattern Recognition · Computer Science 2021-12-03 Zhiqiang Shen , Eric Xing

Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We…

Computation and Language · Computer Science 2023-05-29 Nitay Calderon , Subhabrata Mukherjee , Roi Reichart , Amir Kantor

Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…

Computation and Language · Computer Science 2025-09-19 Yihan Cao , Yanbin Kang , Zhengming Xing , Ruijie Jiang

Machine learning models, particularly the black-box models, are widely favored for their outstanding predictive capabilities. However, they often face scrutiny and criticism due to the lack of interpretability. Paradoxically, their strong…

Methodology · Statistics 2025-09-17 Xuetao Lu , J. Jack Lee

Knowledge distillation from Large Language Models (LLMs) to smaller models has emerged as a critical technique for deploying efficient AI systems. However, current methods for distillation via synthetic data lack pedagogical awareness,…

Artificial Intelligence · Computer Science 2026-02-13 Bowei He , Yankai Chen , Xiaokun Zhang , Linghe Kong , Philip S. Yu , Xue Liu , Chen Ma

Human language understanding operates at multiple levels of granularity (e.g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined. However, existing deep models with stacked layers do…

Computation and Language · Computer Science 2022-03-04 Xiang Hu , Haitao Mi , Zujie Wen , Yafang Wang , Yi Su , Jing Zheng , Gerard de Melo

Significant memory and computational requirements of large deep neural networks restrict their application on edge devices. Knowledge distillation (KD) is a prominent model compression technique for deep neural networks in which the…

Computation and Language · Computer Science 2021-04-16 Aref Jafari , Mehdi Rezagholizadeh , Pranav Sharma , Ali Ghodsi

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Weidong Shi , Guanghui Ren , Yunpeng Chen , Shuicheng Yan

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

Computation and Language · Computer Science 2025-04-04 Kushal Jain , Piyushi Goyal , Kumar Shridhar

In this work, we present the first systematic evaluation of catastrophic forgetting and modality inequivalence in speech large language models, showing that introducing speech capabilities can degrade knowledge and reasoning even when…

Computation and Language · Computer Science 2025-09-19 Enzhi Wang , Qicheng Li , Zhiyuan Tang , Yuhang Jia

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Computation and Language · Computer Science 2020-05-04 Linqing Liu , Huan Wang , Jimmy Lin , Richard Socher , Caiming Xiong