5 papers
Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy
Juyeon Kim, Geon Lee, Dongwon Choi +2
Retrieval over visually rich documents is essential for tasks such as legal discovery, scientific search, and enterprise knowledge management. Existing approaches fall into two par…
ReFuGe: Feature Generation for Prediction Tasks on Relational Databases with LLM Agents
Kyungho Kim, Geon Lee, Juyeon Kim +3
Relational databases (RDBs) play a crucial role in many real-world web applications, supporting data management across multiple interconnected tables. Beyond typical retrieval-orie…
RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases
Dongwon Choi, Sunwoo Kim, Juyeon Kim +5
Recent advances have demonstrated the effectiveness of graph-based learning on relational databases (RDBs) for predictive tasks. Such approaches require transforming RDBs into grap…
KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking
Juyeon Kim, Geon Lee, Taeuk Kim +1
Entity linking (EL) aligns textual mentions with their corresponding entities in a knowledge base, facilitating various applications such as semantic search and question answering.…
Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback
Fatemeh Pesaran Zadeh, Juyeon Kim, Jin-Hwa Kim +1
Large language models (LLMs) have demonstrated strong capabilities across various language tasks, notably through instruction-tuning methods. However, LLMs face challenges in visua…