4 papers · 1 filter
Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
Kyomin Hwang, Hyeonjin Kim, Sangyeon Cho +1
While LLMs are increasingly used in commercial services, they pose privacy risks such as leakage of sensitive personally identifiable information (PII). For LLMs trained on multili…
BioBridge: Unified Bio-Embedding with Bridging Modality in Code-Switched EMR
Jangyeong Jeon, Sangyeon Cho, Dongjoon Lee +2
Pediatric Emergency Department (PED) overcrowding presents a significant global challenge, prompting the need for efficient solutions. This paper introduces the BioBridge framework…
DSG-KD: Knowledge Distillation from Domain-Specific to General Language Models
Sangyeon Cho, Jangyeong Jeon, Dongjoon Lee +2
The use of pre-trained language models fine-tuned to address specific downstream tasks is a common approach in natural language processing (NLP). However, acquiring domain-specific…
ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings
Jangyeong Jeon, Sangyeon Cho, Minuk Ma +1
This paper examines the Code-Switching (CS) phenomenon where two languages intertwine within a single utterance. There exists a noticeable need for research on the CS between Engli…