5 papers
Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment
Keunha Kim, Yoonjin Jang, Hyeon-gu Lee +2
Knowledge graphs (KGs) are increasingly used as structured context for Large Language Models (LLMs), but industrial KG-RAG systems often need to integrate public and domain-specifi…
HyPE: Category-Aware Hypergraph Encoding with Persistent Edge Embeddings for Persona-Grounded Dialogue
Sangwon Youn, Yoonjin Jang, Youngjoong Ko
Persona-grounded dialogue systems aim to produce responses consistent with a speaker's persona, yet existing methods treat personas as a flat set of sentences and fail to model the…
G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents
Minjun Choi, Yoonjin Jang, Sangwon Youn +1
While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context rea…
HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment
Yoonjin Jang, Junwoo Kim, Youngjoong Ko
Entity Alignment (EA) is essential for knowledge graph (KG) fusion, but existing benchmarks often allow models to exploit name overlap rather than relational structure. This makes…
SS-MPC: A Sequence-Structured Multi-Party Conversation System
Yoonjin Jang, Keunha Kim, Youngjoong Ko
Recent Multi-Party Conversation (MPC) models typically rely on graph-based approaches to capture dialogue structures. However, these methods have limitations, such as information l…