Note 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.

Note "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."

Note "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%."

Note "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."

Note "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."

Note see impl: https://github.com/tomasonjo/blogs/blob/master/llm/ms_graphrag.ipynb

Note "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

Note "Extensive experiments demonstrate that both MoG and MoGG effectively predict optimal granularity levels, significantly enhancing the performance of the RAG system in downstream tasks"

Note "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."

Note "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."

Note "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"