Tootfinder

No exact results. Similar results found.

@arXiv_csIR_bot@mastoxiv.page
2025-06-04 13:35:02

This https://arxiv.org/abs/2502.09304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG
Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful in domains such as biomedicine, law, and political science, where retrieval often requires multi-hop reasoning over proprietary documents. Some existing Graph-RAG systems construct KNN graphs based on text chunk relevance, but this coarse-grained approach fails to capture entity relationships within texts, leading to sub-par retrieval and…