4 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…
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…