English
Related papers

Related papers: Short Data, Long Context: Distilling Positional Kn…

200 papers

Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…

Computation and Language · Computer Science 2026-02-17 Manish Dhakal , Uthman Jinadu , Anjila Budathoki , Rajshekhar Sunderraman , Yi Ding

Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the…

Computation and Language · Computer Science 2023-05-18 Siyue Wu , Hongzhan Chen , Xiaojun Quan , Qifan Wang , Rui Wang

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Computation and Language · Computer Science 2023-11-27 Nathan Brown , Ashton Williamson , Tahj Anderson , Logan Lawrence

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Machine Learning · Computer Science 2026-05-12 Ejafa Bassam , Dawei Zhu , Kaigui Bian

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

Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of…

Computation and Language · Computer Science 2024-03-13 Yichuan Li , Xiyao Ma , Sixing Lu , Kyumin Lee , Xiaohu Liu , Chenlei Guo

Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning. However, a key requirement is that training examples are in correspondence across the domains. We show…

Computer Vision and Pattern Recognition · Computer Science 2017-08-30 Jong-Chyi Su , Subhransu Maji

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Nikita Starodubcev , Artem Fedorov , Artem Babenko , Dmitry Baranchuk

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

Sequence-to-sequence tasks often benefit from long contexts, but the quadratic complexity of self-attention in standard Transformers renders this non-trivial. During generation, temporary representations -stored in the so-called KV…

Computation and Language · Computer Science 2025-03-14 Vivek Chari , Guanghui Qin , Benjamin Van Durme

Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation…

Computation and Language · Computer Science 2024-11-26 Yijun Tian , Yikun Han , Xiusi Chen , Wei Wang , Nitesh V. Chawla

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in…

Machine Learning · Computer Science 2019-03-28 Qun Liu , Supratik Mukhopadhyay , Yimin Zhu , Ravindra Gudishala , Sanaz Saeidi , Alimire Nabijiang

In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-student alignment at the logits level. Since high-confidence…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Jiayan Li , Jun Li , Zhourui Zhang , Jianhua Xu

Conventional knowledge distillation (KD) methods require access to the internal information of teachers, e.g., logits. However, such information may not always be accessible for large pre-trained language models (PLMs). In this work, we…

Computation and Language · Computer Science 2023-06-16 Qinhong Zhou , Zonghan Yang , Peng Li , Yang Liu

Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…

Computer Vision and Pattern Recognition · Computer Science 2022-01-13 Thanh Nguyen-Duc , He Zhao , Jianfei Cai , Dinh Phung

This paper presents a novel knowledge distillation method for dialogue sequence labeling. Dialogue sequence labeling is a supervised learning task that estimates labels for each utterance in the target dialogue document, and is useful for…

Computation and Language · Computer Science 2021-11-23 Shota Orihashi , Yoshihiro Yamazaki , Naoki Makishima , Mana Ihori , Akihiko Takashima , Tomohiro Tanaka , Ryo Masumura

Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly representative of the conditions at test time. However, defining,…

Machine Learning · Computer Science 2020-10-06 Samira Abnar , Mostafa Dehghani , Willem Zuidema

So far, expensive finetuning beyond the pretraining sequence length has been a requirement for effectively extending the context of language models (LM). In this work, we break this key bottleneck by Dropping the Positional Embeddings of…

Computation and Language · Computer Science 2025-12-16 Yoav Gelberg , Koshi Eguchi , Takuya Akiba , Edoardo Cetin

Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. This study investigates structuring training data to enhance…

Computation and Language · Computer Science 2025-03-03 Konrad Staniszewski , Szymon Tworkowski , Sebastian Jaszczur , Yu Zhao , Henryk Michalewski , Łukasz Kuciński , Piotr Miłoś

Long-context language models unlock advanced capabilities in reasoning, code generation, and document summarization by leveraging dependencies across extended spans of text. However, a significant portion of readily available long-text data…

Computation and Language · Computer Science 2025-10-31 Haoran Deng , Yingyu Lin , Zhenghao Lin , Xiao Liu , Yizhou Sun , Yi-An Ma , Yeyun Gong
‹ Prev 1 4 5 6 7 8 10 Next ›