Related papers: KDH-MLTC: Knowledge Distillation for Healthcare Mu…
Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large…
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…
In multi-label text classification, each textual document can be assigned with one or more labels. Due to this nature, the multi-label text classification task is often considered to be more challenging compared to the binary or multi-class…
Large pre-trained language models often struggle to incorporate new domain-specific terminology when fine-tuned on small, specialized corpora. In this work, we address the challenge of vocabulary expansion in frozen LLMs by introducing a…
Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key…
This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…
Automatic topic classification has been studied extensively to assist managing and indexing scientific documents in a digital collection. With the large number of topics being available in recent years, it has become necessary to arrange…
Large language models (LLMs) excel at clinical information extraction but their computational demands limit practical deployment. Knowledge distillation--the process of transferring knowledge from larger to smaller models--offers a…
In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teacher model to distill the expert knowledge needed for tagging medical texts in Polish. This work is…
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…
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…
In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many…
Corpus distillation for biomedical large language models (LLMs) seeks to address the pressing challenge of insufficient quantity and quality in open-source annotated scientific corpora, which remains a bottleneck for effective LLM training…
Semi-supervised learning for medical image segmentation presents a unique challenge of efficiently using limited labeled data while leveraging abundant unlabeled data. Despite advancements, existing methods often do not fully exploit the…
Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…
Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…
Large Language Models (LLMs) face significant challenges at inference time due to their high computational demands. To address this, we present Performance-Guided Knowledge Distillation (PGKD), a cost-effective and high-throughput solution…
This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…
With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…