Graph-enhanced RAG
using knowledge graphs in RAG for grounding LLM results
Paper • 2311.07509 • Published • 1Note Excellent analysis of lift from RAG vs. Graph-enhanced RAG on the correctness of *result sets* of SQL query generation (not the queries themselves), e.g., when there's an intermediary graph query used to enhance the SQL generated.
Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!
Paper • 2405.11706 • Published • 1Note "Using the chat with the data benchmark, our primary finding is that our approach increases the overall accuracy to 72% including an additional 8% of "I don't know" unknown results. Thus, the overall error rate is 20%. These results provide further evidence that investing knowledge graphs, namely the ontology, provides higher accuracy for LLM powered question answering systems."
Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering
Paper • 2404.17723 • Published • 1Note "Empirical assessments on our benchmark datasets, utilizing key retrieval (MRR, Recall@K, NDCG@K) and text generation (BLEU, ROUGE, METEOR) metrics, reveal that our method outperforms the baseline by 77.6% in MRR and by 0.32 in BLEU. Our method has been deployed within LinkedIn’s customer service team for approximately six months and has reduced the median per-issue resolution time by 28.6%."
TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
Paper • 2406.11460 • Published • 1Note "Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions."
UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models
Paper • 2406.02110 • Published • 1Note "Experimental findings illustrate that UniOQA notably advances SpCQL Logical Accuracy to 21.2% and Execution Accuracy to 54.9%, achieving the new state-of-the-art results on this benchmark."
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
Paper • 2404.16130 • Published • 1Note see impl: https://github.com/tomasonjo/blogs/blob/master/llm/ms_graphrag.ipynb
DiffKG: Knowledge Graph Diffusion Model for Recommendation
Paper • 2312.16890 • Published • 1Note "graph diffusion" as in generative diffusion (training on ablated sequences), which is super interesting -- not the diffusion in the sense of graph embeddings and Gr
Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation
Paper • 2406.00456 • Published • 1Note "Extensive experiments demonstrate that both MoG and MoGG effectively predict optimal granularity levels, significantly enhancing the performance of the RAG system in downstream tasks"
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
Paper • 2405.20139 • Published • 1Note "Experimental results show that GNN-RAG achieves state-of-the-art performance in two widely used KGQA benchmarks (WebQSP and CWQ), outperforming or matching GPT-4 performance with a 7B tuned LLM. In addition, GNN-RAG excels on multi-hop and multi-entity questions outperforming competing approaches by 8.9--15.5% points at answer F1."
GRAG: Graph Retrieval-Augmented Generation
Paper • 2405.16506 • Published • 1Note "Extensive experiments on graph multi-hop reasoning benchmarks demonstrate that in scenarios requiring multi-hop reasoning on textual graphs, our GRAG approach significantly outperforms current state-of-the-art RAG methods while effectively mitigating hallucinations."
Augmenting Textual Generation via Topology Aware Retrieval
Paper • 2405.17602 • Published • 1Note "Unlike proximity-based topological similarity which considers nodes residing closely in one network to be similar, role-based topological similarity focuses on identifying nodes with topologically similar neighborhoods"
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
Paper • 2402.07630 • Published • 1The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Paper • 2406.01506 • Published • 3Leveraging Large Language Models for Semantic Query Processing in a Scholarly Knowledge Graph
Paper • 2405.15374 • Published • 1Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning
Paper • 2405.16933 • Published • 1Don't Forget to Connect! Improving RAG with Graph-based Reranking
Paper • 2405.18414 • PublishedKG-RAG: Bridging the Gap Between Knowledge and Creativity
Paper • 2405.12035 • Published • 1Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study
Paper • 2404.11792 • Published • 1