5 papers
MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection
Jinmo Han, Jimin Hong, Chanyeong Moon +3
As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse writing s…
SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models
Seonuk Kim, Yonghyeon Jun, Ju Yeon Kang +3
Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data. However, the scarcity of high-quality annotated audio data remain…
The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators
Hawon Jeong, ChaeHun Park, Jimin Hong +2
As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often…
Accelerating Multilingual Language Model for Excessively Tokenized Languages
Jimin Hong, Gibbeum Lee, Jaewoong Cho
Recent advancements in large language models (LLMs) have remarkably enhanced performances on a variety of tasks in multiple languages. However, tokenizers in LLMs trained primarily…
Learning to Diversify Neural Text Generation via Degenerative Model
Jimin Hong, ChaeHun Park, Jaegul Choo
Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address…