Reproduce “GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Maya Arseven, Anette Frank, Beni Egressy, Johann Higl, Moritz Plenz
GLM-RAG uses a pretrained language model adapted to read graph structure and entity and relation text when retrieving evidence for multi-document questions. It selects a local subgraph, encodes its text and connections with the question, and ranks entities to retrieve documents. On zero-shot MultiHopRAG, it achieves 60.0% document Recall@2, versus 39.0% for GFM-RAG+; this advantage is clearest on multi-hop tasks.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.