← Search

Yihua Zhu

2 accepted papers

2026

Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering

AAAI 2026technical

Knowledge Base Question Answering (KBQA) aims to answer natural language questions using structured knowledge from KBs. While LLM-only approaches offer generalization, they suffer from outdated knowledge, hallucinations, and lack of transparency. Chain-based KG-RAG methods address these issues by in

Cited by 0SourcePDFScholar
2024

Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding

EMNLP 2024finding

The primary aim of Knowledge Graph Embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. While rotation-based methods like RotatE and QuatE perform well in KGE, they face two challenges: limited model flexibility requiring proportional i…