Get started
Author

Kaehyun Um

Observed names: KaeHyun Um, Um, Kaehyun
Institution: Yonsei University
Observed institution: Yonsei University
ORCID: 0009-0005-2366-5296
Observed ORCID: 0009-0005-2366-5296
OpenAlex ID: A5115087012
OmEGa( Ω ): Ontology-based information extraction framework for constructing task-centric knowledge graph from manufacturing documents with large language model
2024 · Midan Shim, Hyojun Choi, et al. · Advanced Engineering Informatics · 30
K-EXAONE 2.0 Technical Report
2026 · Choi, Eunbi, Choi, Kibong, et al. · arXiv (Cornell University)
PDF
Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement
2026 · Shim, Midan, Hwang, Seokju, et al. · arXiv (Cornell University)
PDF
RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
2026 · Kaehyun Um, KyuHwan Yeom, et al. · International World Wide Web Conference (WWW)
RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
2026 · Um, Kaehyun, Yeom, KyuHwan, et al. · arXiv (Cornell University)
PDF
RPO-RAG models
2026 · Um, Kaehyun · Zenodo (CERN European Organization for Nuclear Research)
Anchor-Guided Structured Grounding with Cross-Entity Interaction for Grounded Multimodal Named Entity Recognition
2026 · Minji Kim, Yusol Oh, et al. · SSRN Electronic Journal
Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement
2026 · Midan Shim, Seokju Hwang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Data-Efficient Adaptation to Contextual Shifts in LLM-based Conversational Recommendation
2026 · Hyeongjun Yang, Donghyun Kim, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Anchor-Guided Structured Grounding with Cross-Entity Interaction for Grounded Multimodal Named Entity Recognition
2026 · Minji Kim, Yusol Oh, et al. · SSRN Electronic Journal
Works count: 10
Citation count: 30
H-index: 1
I10-index: 1
Year
Topic
Type