Sumyeong Ahn
YOU?
Author Swipe
View article: Dual Debiasing for Noisy In-Context Learning for Text Generation
Dual Debiasing for Noisy In-Context Learning for Text Generation Open
View article: Distributed In-Context Learning under Non-IID Among Clients
Distributed In-Context Learning under Non-IID Among Clients Open
Advancements in large language models (LLMs) have shown their effectiveness in multiple complicated natural language reasoning tasks. A key challenge remains in adapting these models efficiently to new or unfamiliar tasks. In-context learn…
View article: VACoDe: Visual Augmented Contrastive Decoding
VACoDe: Visual Augmented Contrastive Decoding Open
Despite the astonishing performance of recent Large Vision-Language Models (LVLMs), these models often generate inaccurate responses. To address this issue, previous studies have focused on mitigating hallucinations by employing contrastiv…
View article: FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning
FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning Open
Federated Learning (FL) has emerged as a pivotal framework for the development of effective global models (global FL) or personalized models (personalized FL) across clients with heterogeneous, non-iid data distribution. A key challenge in…
View article: Augmented Risk Prediction for the Onset of Alzheimer's Disease from Electronic Health Records with Large Language Models
Augmented Risk Prediction for the Onset of Alzheimer's Disease from Electronic Health Records with Large Language Models Open
Alzheimer's disease (AD) is the fifth-leading cause of death among Americans aged 65 and older. Screening and early detection of AD and related dementias (ADRD) are critical for timely intervention and for identifying clinical trial partic…
View article: Comparison of Prompt Engineering and Fine-Tuning Strategies in Large Language Models in the Classification of Clinical Notes
Comparison of Prompt Engineering and Fine-Tuning Strategies in Large Language Models in the Classification of Clinical Notes Open
The emerging large language models (LLMs) are actively evaluated in various fields including healthcare. Most studies have focused on established benchmarks and standard parameters; however, the variation and impact of prompt engineering a…
View article: Large Language Models in Medical Term Classification and Unexpected Misalignment Between Response and Reasoning
Large Language Models in Medical Term Classification and Unexpected Misalignment Between Response and Reasoning Open
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3.5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (MCI) from discharge summaries and examines instances where …
View article: Active Prompt Learning in Vision Language Models
Active Prompt Learning in Vision Language Models Open
Pre-trained Vision Language Models (VLMs) have demonstrated notable progress in various zero-shot tasks, such as classification and retrieval. Despite their performance, because improving performance on new tasks requires task-specific kno…
View article: Fine tuning Pre trained Models for Robustness Under Noisy Labels
Fine tuning Pre trained Models for Robustness Under Noisy Labels Open
The presence of noisy labels in a training dataset can significantly impact the performance of machine learning models. To tackle this issue, researchers have explored methods for Learning with Noisy Labels to identify clean samples and re…
View article: NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models Open
Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers. Despite the versatility of encoder-decoder models in numerous NLP tasks, th…
View article: Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels
Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels Open
Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved gen…
View article: CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition
CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition Open
Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to ba…
View article: NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models Open
Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers. Despite the versatility of encoder-decoder models in numerous NLP tasks, th…
View article: Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels
Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels Open
Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved gen…
View article: Mitigating Dataset Bias by Using Per-sample Gradient
Mitigating Dataset Bias by Using Per-sample Gradient Open
The performance of deep neural networks is strongly influenced by the training dataset setup. In particular, when attributes having a strong correlation with the target attribute are present, the trained model can provide unintended prejud…
View article: Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation
Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation Open
In this paper, we study the problem of unsupervised domain adaptation that aims at obtaining a prediction model for the target domain using labeled data from the source domain and unlabeled data from the target domain. There exists an arra…