4 papers
Large Language Models Facilitate Vision Reflection in Image Classification
Guoyuan An, JaeYoon Kim, SungEui Yoon
This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the predicti…
KoBALT: Korean Benchmark For Advanced Linguistic Tasks
Hyopil Shin, Sangah Lee, Dongjun Jang +9
We introduce KoBALT (Korean Benchmark for Advanced Linguistic Tasks), a comprehensive linguistically-motivated benchmark comprising 700 multiple-choice questions spanning 24 phenom…
MoFE: Mixture of Frozen Experts Architecture
Jean Seo, Jaeyoon Kim, Hyopil Shin
We propose the Mixture of Frozen Experts (MoFE) architecture, which integrates Parameter-efficient Fine-tuning (PEFT) and the Mixture of Experts (MoE) architecture to enhance both…
How does a Language-Specific Tokenizer affect LLMs?
Jean Seo, Jaeyoon Kim, SungJoo Byun +1
The necessity of language-specific tokenizers intuitively appears crucial for effective natural language processing, yet empirical analyses on their significance and underlying rea…