5 papers
LED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis
Inbum Heo, Taewook Hwang, Jeesu Jung +1
Recent advancements in Document Layout Analysis through Large Language Models and Multimodal Models have significantly improved layout detection. However, despite these improvement…
LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis
Inbum Heo, Taewook Hwang, Jeesu Jung +1
Recent advances in Large Language Models (LLMs) and Large Multimodal Models (LMMs) have improved Document Layout Analysis (DLA), yet structural errors such as region merging, split…
Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero-Data-Leakage Setting
Goun Pyeon, Inbum Heo, Jeesu Jung +7
This study systematically evaluated the mathematical reasoning capabilities of Large Language Models (LLMs) using the 2026 Korean College Scholastic Ability Test (CSAT) Mathematics…
Reasoning Steps as Curriculum: Using Depth of Thought as a Difficulty Signal for Tuning LLMs
Jeesu Jung, Sangkeun Jung
Curriculum learning for training LLMs requires a difficulty signal that aligns with reasoning while remaining scalable and interpretable. We propose a simple premise: tasks that de…
ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction
Jeesu Jung, Chanjun Park, Sangkeun Jung
Recent efforts in LLM alignment have focused on constructing large-scale preference datasets via human or Artificial Intelligence (AI) annotators. However, such approaches rely on…