Agentic Intelligence for Structured Knowledge Retrieval

Project Description

Many real-world AI systems need to use structured knowledge rather than relying on generated text alone. This project explores agentic intelligence for structured knowledge retrieval, with an emphasis on helping users ask questions, review relevant evidence, and obtain more grounded responses.

The project studies evidence-guided reasoning with structured knowledge, including workflows for asking questions, reviewing retrieved context, and inspecting how structured knowledge can support more transparent AI-assisted discovery and decision-making. Public notes are intentionally kept at a high level while implementation details remain shared through collaboration channels.

  • Utility: Use structured knowledge to support more grounded AI responses.
  • Trustworthiness: Make retrieved evidence easier to inspect and verify.
  • Diversity: Support broader exploration across related concepts and evidence.

Together, these directions aim to make structured knowledge retrieval more transparent, useful, and easier to apply across scientific and decision-making workflows.

Publications

  • Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
    Zhisheng Qi, Utkarsh Sahu, Li Ma, Haoyu Han, Ryan Rossi, Franck Dernoncourt, Mahantesh Halappanavar, Nesreen Ahmed, Yushun Dong, Yue Zhao, Yu Zhang, Yu Wang.
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Dataset and Benchmark Track (KDD), 2026.
    [Paper] [Code]
    Oral Presentation (4.5%)

  • RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
    Haoyu Han, Harry Shomer, Yu Wang, Yongjia Lei, Kai Guo, Zhigang Hua, Bo Long, Hui Liu, Jiliang Tang.
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Dataset and Benchmark Track (KDD), 2026.
    [Paper] [Code]

  • Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
    Kai Guo, Xinnan Dai, Shenglai Zeng, Harry Shomer, Haoyu Han, Yu Wang, Jiliang Tang.
    Empirical Methods in Natural Language Processing (EMNLP), 2026.
    [Paper]

  • Empowering GraphRAG with Knowledge Filtering and Integration
    Kai Guo, Harry Shomer, Shenglai Zeng, Haoyu Han, Yu Wang, Jiliang Tang.
    Empirical Methods in Natural Language Processing (EMNLP), 2025.
    [Paper]

  • Building Transparency in Deep Learning-Powered Network Traffic Classification: A Traffic-Explainer Framework
    Riya Ponraj, Ram Durairajan, Yu Wang.
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD), 2026.
    [Paper] [Code]

  • Rule Mining and Learning for Structured Knowledge Retrieval
    Yongjia Lei, Mahantesh M Halappanavar, Yu Wang.
    ACM International Conference on Web Search and Data Mining (WSDM), 2026.

  • Knowledge Homophily in Large Language Models
    Utkarsh Sahu, Zhisheng Qi, Mahantesh M Halappanavar, Nedim Lipka, Ryan A Rossi, Franck Dernoncourt, Yu Zhang, Yao Ma, Yu Wang.
    ACM International Conference on Web Search and Data Mining (WSDM), 2026.
    [Paper] [Code]

  • Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
    Bo Ni, Zheyuan Liu, Leyao Wang, Yongjia Lei, Yuying Zhao, Xueqi Cheng, Qingkai Zeng, Luna Dong, Yinglong Xia, Krishnaram Kenthapadi, Ryan Rossi, Franck Dernoncourt, Md Mehrab Tanjim, Nesreen Ahmed, Xiaorui Liu, Wenqi Fan, Erik Blasch, Yu Wang, Meng Jiang, Tyler Derr.
    ACM Computing Surveys (CSUR), 2026.
    [Paper] [Code]

  • Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
    Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M. Halappanavar, Jiliang Tang, Yu Wang.
    Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
    [Paper] [Code]
    Best Poster Honorable Mention at SDM’25 Doctoral Forum

Preprints

  • Retrieval-Augmented Generation with Graphs (GraphRAG)
    Yu Wang, Haoyu Han, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A. Rossi, Subhabrata Mukherjee, Xianfeng Tang, Qi He, Zhigang Hua, Bo Long, Tong Zhao, Neil Shah, Amin Javari, Yinglong Xia, Jiliang Tang.
    arXiv, 2025.
    [Paper] [Paper List]

  • RL-Index: Reinforcement Learning for Retrieval Index Reasoning
    Yongjia Lei, Nedim Lipka, Zhisheng Qi, Utkarsh Sahu, Koustava Goswami, Franck Dernoncourt, Ryan A. Rossi, Yu Wang.
    arXiv, 2026.
    [Paper]

  • Benchmarking Multi-Modal Graph-Based Social Media Popularity Prediction
    Utkarsh Sahu, Zhisheng Qi, Li Zhu, Yizhao Yang, Jun Li, Ryan Rossi, Yu Wang.
    arXiv, 2026.
    [Paper]

  • Sparse Personalized Text Generation with Multi-Trajectory Reasoning
    Bo Ni, Haowei Fu, Qinwen Ge, Franck Dernoncourt, Samyadeep Basu, Nedim Lipka, Seunghyun Yoon, Yu Wang, Nesreen K. Ahmed, Subhojyoti Mukherjee, Puneet Mathur, Ryan A. Rossi, Tyler Derr.
    arXiv, 2026.
    [Paper]

Tutorials and Workshops

Workshops

Tutorials

Awards and Honors

Core Project Team

Team PI: Yu Wang

Team Members: Zhisheng Qi, Yongjia Lei, Utkarsh Sahu

Acknowledgements

We thank all our academic and industrial collaborators for their support. This work is supported by the National Science Foundation through III 2524379 and NAIRR250188. Any opinions, findings, conclusions, or recommendations expressed here are those of the authors and do not necessarily reflect the views of the National Science Foundation.

Contact

Yu Wang: Yu.Wang6@uga.edu