Can blocking help in RAG-based entity matching? Check out our preprint "Cost-efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration." We introduce a cost-efficient RAG for EM that reduces the cost of RAG4EM via blocking-based batch retrieval and inference. arxiv.org/abs/2602.05708
On Dec 2, I will be at the #ELLIS UnConference and #EurIPS, presenting our #EMNLP25 paper "Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities" at the UnConference poster session. It would be great to see you there and get a chance to talk in person.
Excited to share that our survey paper "Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities" has been accepted to the #EMNLP2025 main conference. Stay tuned for the camera-ready version.
New preprint: LLMs Meet KGs for QA. In this survey, we systematically study the advances in synthesizing #LLMs and #KGs for #QA. We summarize the evaluation metrics & datasets, and highlight open challenges and opportunities.
Preprint: arxiv.org/abs/2505.20099
Resource: github.com/machuangtao/...
We were thrilled that our tutorial on unifying #LLMs with #KGs for QA at #EDBT2025 attracted a large number of attendees from the #EDBT community, which exceeded our expectations. The slides and materials are now available at: machuangtao.github.io/LLM-KG4QA/tu...
I will be co-presenting a tutorial on Unifying LLMs and Knowledge Graphs for Question Answering at #EDBT2025 with Yongrui Chen, Tianxing Wu, Arijit Khan, and Haofen Wang on March 27, 2025. Join us if you are attending EDBT2025 and are interested in the intersection of #LLMs and #KGs for QA!
