English
Related papers

Related papers: Honey, I Shrunk the Language Model: Impact of Know…

200 papers

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

Deep Neural Networks (DNNs) have achieved notable performance in the fields of computer vision and natural language processing with various applications in both academia and industry. However, with recent advancements in DNNs and…

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Machine Learning · Computer Science 2021-11-16 Raed Alharbi , Minh N. Vu , My T. Thai

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

Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading…

Computation and Language · Computer Science 2026-05-21 Jeonghye Kim , Xufang Luo , Minbeom Kim , Sangmook Lee , Dohyung Kim , Jiwon Jeon , Dongsheng Li , Yuqing Yang

Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this work, we present DistilQwen2.5, a family of distilled,…

Computation and Language · Computer Science 2025-04-22 Chengyu Wang , Junbing Yan , Yuanhao Yue , Jun Huang

Modern language models have the capacity to store and use immense amounts of knowledge about real-world entities, but it remains unclear how to update such knowledge stored in model parameters. While prior methods for updating knowledge in…

Computation and Language · Computer Science 2023-11-01 Shankar Padmanabhan , Yasumasa Onoe , Michael J. Q. Zhang , Greg Durrett , Eunsol Choi

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Computation and Language · Computer Science 2024-12-19 Tianyu Peng , Jiajun Zhang

In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and…

Computation and Language · Computer Science 2024-10-22 Xiaohan Xu , Ming Li , Chongyang Tao , Tao Shen , Reynold Cheng , Jinyang Li , Can Xu , Dacheng Tao , Tianyi Zhou

Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of…

Computation and Language · Computer Science 2025-10-08 Muyu He , Muhammad Ali Shafique , Anand Kumar , Tsach Mackey , Nazneen Rajani

Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily…

Computation and Language · Computer Science 2024-07-26 Joe Stacey , Marek Rei

Human Activity Recognition (HAR) is a central problem for context-aware applications, especially for smart homes and assisted living. A few very recent studies have shown that Large Language Models (LLMs) can be used for HAR at home,…

Artificial Intelligence · Computer Science 2026-01-13 Julien Cumin , Oussama Er-Rahmany , Xi Chen

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Machine Learning · Computer Science 2021-04-26 Sourav Mishra , Suresh Sundaram

In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and its dependence on student and teacher architectures. Starting with the observation that more accurate teachers often don't make good teachers, we…

Machine Learning · Computer Science 2019-10-04 Jang Hyun Cho , Bharath Hariharan

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…

Computation and Language · Computer Science 2021-09-20 Geondo Park , Gyeongman Kim , Eunho Yang

Large language models (LLMs) have shown incredible performance in completing various real-world tasks. The current paradigm of knowledge learning for LLMs is mainly based on learning from examples, in which LLMs learn the internal rule…

Computation and Language · Computer Science 2024-12-17 Wenkai Yang , Yankai Lin , Jie Zhou , Ji-Rong Wen

In-context learning (ICL) allows large language models (LLMs) to solve novel tasks without weight updates. Despite its empirical success, the mechanism behind ICL remains poorly understood, limiting our ability to interpret, improve, and…

Machine Learning · Computer Science 2025-06-16 Chengye Li , Haiyun Liu , Yuanxi Li

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

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun