4 papers across 3 sessions
KARMA is a multi-agent LLM framework that automatically update and expand knowledge graphs from scientific papers. By using nine specialized agents, KARMA successfully add new entities with high verified accuracy and reduce inconsistencies.
NeuSymEA combines symbolic and neural models in a neuro-symbolic framework to robustly align entities across knowledge graphs, improving effectiveness, robustness, and interpretability.
NeuroPath is a RAG framework inspired by brain path navigation. It tracks semantic paths and refines retrieval via LLM reasoning, enhancing semantic coherence and reducing noise, achieves state-of-the-art performance on multi-hop QA.