English
Related papers

Related papers: Rethinking Kullback-Leibler Divergence in Knowledg…

200 papers

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

Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosting the capabilities of smaller models through knowledge distillation (KD) from these powerful yet…

Computation and Language · Computer Science 2024-11-12 Hongzhan Chen , Ruijun Chen , Yuqi Yi , Xiaojun Quan , Chenliang Li , Ming Yan , Ji Zhang

Discriminator Guidance has become a popular method for efficiently refining pre-trained Score-Matching Diffusion models. However, in this paper, we demonstrate that the standard implementation of this technique does not necessarily lead to…

Machine Learning · Computer Science 2025-06-12 Alexandre Verine , Ahmed Mehdi Inane , Florian Le Bronnec , Benjamin Negrevergne , Yann Chevaleyre

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 solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…

Computation and Language · Computer Science 2025-04-16 Xue Zhang , Songming Zhang , Yunlong Liang , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Estimating the Kullback-Leibler (KL) divergence between random variables is a fundamental problem in statistical analysis. For continuous random variables, traditional information-theoretic estimators scale poorly with dimension and/or…

Machine Learning · Computer Science 2025-10-08 Mikil Foss , Andrew Lamperski

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

In this paper, we present EasyDistill, a comprehensive toolkit designed for effective black-box and white-box knowledge distillation (KD) of large language models (LLMs). Our framework offers versatile functionalities, including data…

Computation and Language · Computer Science 2025-06-30 Chengyu Wang , Junbing Yan , Wenrui Cai , Yuanhao Yue , Jun Huang

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…

Computation and Language · Computer Science 2022-11-03 Haojie Pan , Chengyu Wang , Minghui Qiu , Yichang Zhang , Yaliang Li , Jun Huang

Autoregressive large language models (LLMs) pre-trained by next token prediction are inherently proficient in generative tasks. However, their performance on knowledge-driven tasks such as factual knowledge querying remains unsatisfactory.…

Computation and Language · Computer Science 2026-01-14 Peng Yu , Cheng Deng , Beiya Dai , Xinbing Wang , Ying Wen

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek KL divergence…

Machine Learning · Computer Science 2022-03-01 Parikshit Gopalan , Nina Narodytska , Omer Reingold , Vatsal Sharan , Udi Wieder

We propose a Kullback-Leibler Divergence (KLD) filter to extract anomalies within data series generated by a broad class of proximity sensors, along with the anomaly locations and their relative sizes. The technique applies to devices…

Signal Processing · Electrical Eng. & Systems 2024-05-07 Ruikun Zhou , Wail Gueaieb , Davide Spinello

Learning word representations has garnered greater attention in the recent past due to its diverse text applications. Word embeddings encapsulate the syntactic and semantic regularities of sentences. Modelling word embedding as multi-sense…

Computation and Language · Computer Science 2019-11-15 P. Jayashree , Ballijepalli Shreya , P. K. Srijith

Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we…

Computation and Language · Computer Science 2025-09-26 Bo Zhang , Hui Ma , Dailin Li , Jian Ding , Jian Wang , Bo Xu , HongFei Lin

Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Huan Wang , Suhas Lohit , Michael Jones , Yun Fu

Data allocation plays a critical role in federated large language model (LLM) and small language models (SLMs) reasoning collaboration. Nevertheless, existing data allocation methods fail to address an under-explored challenge in…

Artificial Intelligence · Computer Science 2026-02-24 Wei Guo , Siyuan Lu , Xiangdong Ran , Yiqi Tong , Yikun Ban , Zelong Xu , Jing Fan , Zixuan Huang , Xiao Zhang , Zhaojun Hu , Fuzhen Zhuang

Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities. Although some priors introduce Knowledge Distillation to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Ze Feng , Sen Yang , Boqiang Duan , Wankou Yang , Jingdong Wang

This paper aims to explore the potential of combining Deep Reinforcement Learning (DRL) with Knowledge Distillation (KD) by distilling various DRL algorithms and studying their distillation effects. By doing so, the computational burden of…

Machine Learning · Computer Science 2024-04-03 Guanlin Meng

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Machine Learning · Computer Science 2026-04-13 Zhaoyang Zhang , Shuli Jiang , Yantao Shen , Yuting Zhang , Dhananjay Ram , Shuo Yang , Zhuowen Tu , Wei Xia , Stefano Soatto

Large Language Models (LLMs) have shown impressive results on a variety of text understanding tasks. Search queries though pose a unique challenge, given their short-length and lack of nuance or context. Complicated feature engineering…

Computation and Language · Computer Science 2022-10-31 Krishna Srinivasan , Karthik Raman , Anupam Samanta , Lingrui Liao , Luca Bertelli , Mike Bendersky