2025
D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering
EMNLP 2025
Knowledge Graph Question Answering (KGQA) aims to answer natural language questions based on knowledge graphs.Recent approaches apply the Retrieval-Augmented Generation (RAG) paradigm to incorporate Large Language Models (LLMs) to this task, where a retriever selects a question-related subgraph and