Shenghua Liu

Professor, Trustworthy LLM and Big Graph Mining

sliu.png

No.6 Kexueyuan South Road, Haidian District

Beijing, China 100190

[short bio] [group page]

email: liushenghua at ict.ac.cn

I am a Professor at Institute of Computing Technology, Chinese Academy of Sciences. My research interests include trustworthy foundation model and big graph mining with applications in scientific deep research, anomaly detection, and various real-world networked systems ranging from academic collaborations, supply chain, financial transactions and biological networks. The arising of LLMs drives most of the interests to trustworthy foundation models, and graph LLMs which scale LLM the ability to understand graphs, to think and model with graphs. Believing that with graph LLMs, real-world problems with complex correlations and connections can be well and trustworthily solved.

The featured works are published on IEEE TKDE, ACM TKDD, and proceedings of top-tier conferences such as AAAI, ICLR, ACL, CIKM, WSDM, ECML-PKDD, etc. Some of the publications are recognized as ASP-DAC 2010 best paper candidate, ECML-PKDD 2020 best student DM paper award.

My educational and visiting experience:

news

May 16, 2025 Two of our works are accepted by ACL main 2025.

selected publications

  1. Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts
    Baolong Bi, Shenghua Liu, Lingrui Mei, and 4 more authors
    In In Proc. of the Association for Computational Linguistics, ACL Main, 2025
  2. Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
    Yuyao Ge, Shenghua Liu, Baolong Bi, and 5 more authors
    In In Proc. of the Association for Computational Linguistics, ACL Main, 2025
  3. Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
    Baolong Bi, Shenghua Liu, Yiwei Wang, and 5 more authors
    In International Conference on Learning Representations, ICLR, 2025
  4. "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models’ Jailbreak
    Lingrui Mei, Shenghua Liu, Yiwei Wang, and 3 more authors
    In In Proc. of the International Conference on Computational Linguistics, Coling, 2025
  5. SLANG: New Concept Comprehension of Large Language Models
    Lingrui Mei, Shenghua Liu, Yiwei Wang, and 2 more authors
    In In Proc. of the Empirical Methods in Natural Language Processing, EMNLP Main, 2024
  6. Node Embedding Preserving Graph Summarization
    Houquan Zhou, Shenghua Liu, Huawei Shen, and 1 more author
    ACM Transactions on Knowledge Discovery from Data, TKDD, 2024
  7. Graph Summarization for Preserving Spectral Characteristics
    Houquan Zhou, Shenghua Liu, Huawei Shen, and 1 more author
    In In Proc. of the SIAM International Conference on Data Mining, SDM, 2024
  8. Unified Dense Subgraph Detection: Fast Spectral Theory based Algorithms
    Wenjie Feng, Shenghua Liu, Danai Koutra, and 1 more author
    IEEE Transactions on Knowledge and Data Engineering, TKDE, 2024
    Published March 2024 (pub date: 17 July 2023)
  9. Time Series Anomaly Detection with Adversarial Reconstruction Networks
    Shenghua Liu, Bin Zhou, Quan Ding, and 4 more authors
    IEEE Transactions on Knowledge and Data Engineering, TKDE, 2023
  10. SpecGreedy: Unified Dense Subgraph Detection
    Wenjie Feng, Shenghua Liu, Danai Koutra, and 2 more authors
    In In Proc. of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD, 2020
    Best student DM paper award. Acceptance rate: 19%. Verified on 40 real-world networks, and a 1.47-billion-edge graph
  11. A Contrast Metric for Fraud Detection in Rich Graphs
    Shenghua Liu, Bryan Hooi, and Christos Faloutsos
    IEEE Transactions on Knowledge and Data Engineering, TKDE, 2019
  12. HoloScope: Topology-and-Spike Aware Fraud Detection
    Shenghua Liu, Bryan Hooi, and Christos Faloutsos
    In In Proc. of the ACM International Conference on Information and Knowledge Management, CIKM, 2017