English
Related papers

Related papers: Bridging the Gap between Decision and Logits in De…

200 papers

Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a…

Machine Learning · Computer Science 2024-12-04 Chengting Yu , Fengzhao Zhang , Ruizhe Chen , Aili Wang , Zuozhu Liu , Shurun Tan , Er-Ping Li

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Computation and Language · Computer Science 2025-04-08 Yixing Li , Yuxian Gu , Li Dong , Dequan Wang , Yu Cheng , Furu Wei

Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-training faces efficiency, flexibility, and effectiveness…

Computation and Language · Computer Science 2025-03-20 Yuxian Gu , Hao Zhou , Fandong Meng , Jie Zhou , Minlie Huang

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Computation and Language · Computer Science 2024-07-18 Songming Zhang , Yunlong Liang , Shuaibo Wang , Wenjuan Han , Jian Liu , Jinan Xu , Yufeng Chen

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Computation and Language · Computer Science 2023-01-31 Jan Philip Wahle

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research…

Information Retrieval · Computer Science 2024-08-28 Nikhil Khani , Shuo Yang , Aniruddh Nath , Yang Liu , Pendo Abbo , Li Wei , Shawn Andrews , Maciej Kula , Jarrod Kahn , Zhe Zhao , Lichan Hong , Ed Chi

Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…

Computation and Language · Computer Science 2021-01-01 Ahmad Rashid , Vasileios Lioutas , Abbas Ghaddar , Mehdi Rezagholizadeh

Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillation (KD) is a prominent method for this, research on KD for…

Computation and Language · Computer Science 2024-09-30 Gyeongman Kim , Doohyuk Jang , Eunho Yang

Deploying large language models (LLMs) of several billion parameters can be impractical in most industrial use cases due to constraints such as cost, latency limitations, and hardware accessibility. Knowledge distillation (KD) offers a…

Computation and Language · Computer Science 2025-01-28 Nicolas Boizard , Kevin El Haddad , Céline Hudelot , Pierre Colombo

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Computation and Language · Computer Science 2025-08-05 Suhas Kamasetty Ramesh , Ayan Sengupta , Tanmoy Chakraborty

Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning…

Computation and Language · Computer Science 2022-11-03 Lean Wang , Lei Li , Xu Sun

Knowledge distillation has proven effective for model compression by transferring knowledge from a larger network called the teacher to a smaller network called the student. Current knowledge distillation in time series is predominantly…

Machine Learning · Computer Science 2026-01-12 Nilushika Udayangani Hewa Dehigahawattage , Kishor Nandakishor , Marimuthu Palaniswami

We introduce the problem of continual distillation learning (CDL) in order to use knowledge distillation (KD) to improve prompt-based continual learning (CL) models. The CDL problem is valuable to study since the use of a larger vision…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Qifan Zhang , Yunhui Guo , Yu Xiang

In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance.…

Machine Learning · Computer Science 2023-11-07 Alex Wilf , Alex Tianyi Xu , Paul Pu Liang , Alexander Obolenskiy , Daniel Fried , Louis-Philippe Morency

Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models…

Computation and Language · Computer Science 2026-02-03 Yuxian Gu , Li Dong , Furu Wei , Minlie Huang

Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to…

Machine Learning · Computer Science 2026-01-16 Sungmin Cha , Kyunghyun Cho

Knowledge distillation is a technique to imitate a performance that a deep learning model has, but reduce the size on another model. It applies the outputs of a model to train another model having comparable accuracy. These two distinct…

Machine Learning · Computer Science 2025-03-13 Kazuhiro Matsuyama , Usman Anjum , Satoko Matsuyama , Tetsuo Shoda , Justin Zhan

Compared with the feature-based distillation methods, logits distillation can liberalize the requirements of consistent feature dimension between teacher and student networks, while the performance is deemed inferior in face recognition.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Weisong Zhao , Xiangyu Zhu , Kaiwen Guo , Xiao-Yu Zhang , Zhen Lei

Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Penghui Yang , Chen-Chen Zong , Sheng-Jun Huang , Lei Feng , Bo An

Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Nicholas Cooper , Lijun Chen , Sailesh Dwivedy , Danna Gurari