Publications

Baolong Bi, Shenghua Liu, Yiwei Wang, Siqian Tong, Lingrui Mei, Yuyao Ge, Yilong Xu, Jiafeng Guo, Xueqi Cheng (2025). Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning. CoRR, 2025, vol. abs/2511.12344.

Yuyao Ge, Lingrui Mei, Zenghao Duan, Tianhao Li, Yujia Zheng, Yiwei Wang, Lexin Wang, Jiayu Yao, Tianyu Liu, Yujun Cai, Baolong Bi, Fangda Guo, Jiafeng Guo, Shenghua Liu, Xueqi Cheng (2025). A Survey of Vibe Coding with Large Language Models. arXiv preprint arXiv:2510.12399.

Jiayu Yao, Shenghua Liu, Yiwei Wang, Rundong Cheng, Lingrui Mei, Baolong Bi, Zhen Xiong, Xueqi Cheng (2025). Not in Sync: Unveiling Temporal Bias in Audio Chat Models. arXiv preprint arXiv:2510.12185, 2025.

Yuyao Ge, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Xuanshan Zhou, Jiayu Yao, Jiafeng Guo, Xueqi Cheng (2025). Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning. arXiv preprint arXiv:2509.06461.

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu (2025). Context-DPO: Aligning Language Models for Context-Faithfulness. Findings of the Association for Computational Linguistics: ACL 2025.

Lingrui Mei, Jiayu Yao, Yuyao Ge, Yiwei Wang, Baolong Bi, Yujun Cai, Jiazhi Liu, Mingyu Li, Zhong-Zhi Li, Duzhen Zhang, Chenlin Zhou, Jiayi Mao, Tianze Xia, Jiafeng Guo, Shenghua Liu (2025). A Survey of Context Engineering for Large Language Models. arXiv preprint arXiv:2507.13334.

Baolong Bi, Shenghua Liu, Xingzhang Ren, Dayiheng Liu, Junyang Lin, Yiwei Wang, Lingrui Mei, Junfeng Fang, Jiafeng Guo, Xueqi Cheng (2025). RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs. CoRR, 2025, vol. abs/2503.15888.

Yuyao Ge, Shenghua Liu, Baolong Bi, Yiwei Wang, Lingrui Mei, Wenjie Feng, Lizhe Chen, Xueqi Cheng (2025). Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?. Proc. of the Association for Computational Linguistics, ACL Main, 2025.

PDF Cite Code DOI ACL Anthology arXiv Website

Jiayu Yao, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Yuyao Ge, Zhecheng Li, Xueqi Cheng (2025). Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation. Proc. of the Empirical Methods in Natural Language Processing, EMNLP Main, 2025, pages 15194–15204.

Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Pengliang Ji, Xueqi Cheng (2025). Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025).

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Xueqi Cheng (2025). Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness Benchmark. The Thirteenth International Conference on Learning Representations (ICLR 2025).

Baolong Bi, Shenghua Liu, Yiwei Wang, Yilong Xu, Junfeng Fang, Lingrui Mei, Xueqi Cheng (2025). Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models. CoRR, 2025, vol. abs/2503.15888.

Yuyao Ge, Shenghua Liu, Yiwei Wang, Lingrui Mei, Lizhe Chen, Baolong Bi, Xueqi Cheng (2025). Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking. CoRR, 2025, vol. abs/2503.19602.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge, Jun Wan, Yurong Wu, Xueqi Cheng (2025). a1: Steep Test-time Scaling Law via Environment Augmented Generation. arXiv preprint arXiv:2504.14597, 2025.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, Xueqi Cheng (2025). "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak. Proc. of the International Conference on Computational Linguistics, Coling, 2025, pages 2144-2162.

Wenjie Feng, Shenghua Liu, Danai Koutra, Xueqi Cheng (2024). Unified Dense Subgraph Detection: Fast Spectral Theory Based Algorithms. IEEE Transactions on Knowledge and Data Engineering, TKDE, 2024, vol. 36, no. 3, pages 1356-1370.

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Hongcheng Gao, Junfeng Fang, Xueqi Cheng (2024). StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models. CoRR, 2024, vol. abs/2409.10132.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Xueqi Cheng (2024). SLANG: New Concept Comprehension of Large Language Models. Proc. of the Empirical Methods in Natural Language Processing, EMNLP Main, 2024, pages 12559-12575.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Xueqi Chen (2024). SLANG: New Concept Comprehension of Large Language Models. CoRR, 2024, vol. abs/2401.12585.

Houquan Zhou, Shenghua Liu, Huawei Shen, Xueqi Cheng (2024). Node Embedding Preserving Graph Summarization. ACM Transactions on Knowledge Discovery from Data, TKDD, 2024, vol. 18, no. 6, pages 1-19.

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Xueqi Cheng (2024). LPNL: Scalable Link Prediction with Large Language Models. Proc. of the Empirical Methods in Natural Language Processing, EMNLP Findings, 2024, pages 3615-3625.

Wenjie Feng, Li Wang, Bryan Hooi, See-Kiong Ng, Shenghua Liu (2024). Interrelated Dense Pattern Detection in Multilayer Networks. IEEE Transactions on Knowledge and Data Engineering, TKDE, 2024, vol. 36, no. 11, pages 6462-6476.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Ruibin Yuan, Xueqi Cheng (2024). HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router. CoRR, 2024, vol. abs/2410.02684.

Houquan Zhou, Shenghua Liu, Huawei Shen, Xueqi Cheng (2024). Graph Summarization for Preserving Spectral Characteristics. Proc. of the SIAM International Conference on Data Mining, SDM, 2024, pages 271-279.

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Hongcheng Gao, Yilong Xu, Xueqi Cheng (2024). Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities. Proc. of the Empirical Methods in Natural Language Processing, EMNLP Findings, 2024, pages 11071-11083.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, Xueqi Cheng (2024). "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak. CoRR, 2024, vol. abs/2406.11668.

Shenghua Liu, Bin Zhou, Quan Ding, Bryan Hooi, Zhengbo Zhang, Huawei Shen, Xueqi Cheng (2023). Time Series Anomaly Detection With Adversarial Reconstruction Networks. IEEE Transactions on Knowledge and Data Engineering, TKDE, 2023, vol. 35, no. 4, pages 4293-4306.

Wenjie Feng, Shenghua Liu, Xueqi Cheng (2023). Hierarchical Dense Pattern Detection in Tensors. ACM Transactions on Knowledge Discovery from Data, TKDD, 2023, vol. 17, no. 6, pages 1-29.

Yugao Zhu, Shenghua Liu, Wenjie Feng, Xueqi Cheng (2023). Fast Searching The Densest Subgraph And Decomposition With Local Optimality. CoRR, 2023, vol. abs/2307.15969.

Houquan Zhou, Shenghua Liu, Danai Koutra, Huawei Shen, Xueqi Cheng (2023). A Provable Framework of Learning Graph Embeddings via Summarization. Proc. of the Association for the Advancement of Artificial Intelligence, AAAI, 2023, pages 4946-4953.

Cite DOI PDF Slides

Quan Ding, Shenghua Liu, Bin Zhou, Huawei Shen, Xueqi Cheng (2022). Multi-scale Anomaly Detection for Big Time Series of Industrial Sensors. CoRR, 2022, vol. abs/2204.08159.

Xiaobing Sun, Wenjie Feng, Shenghua Liu, Yuyang Xie, Siddharth Bhatia, Bryan Hooi, Wenhan Wang, Xueqi Cheng (2022). MonLAD: Money Laundering Agents Detection in Transaction Streams. Proc. of the ACM International Conference on Web Search and Data Mining, WSDM, 2022, pages 976-986.

Xiaobing Sun, Wenjie Feng, Shenghua Liu, Yuyang Xie, Siddharth Bhatia, Bryan Hooi, Wenhan Wang, Xueqi Cheng (2022). MonLAD: Money Laundering Agents Detection in Transaction Streams. CoRR, 2022, vol. abs/2201.10051.

Houquan Zhou, Shenghua Liu, Danai Koutra, Huawei Shen, Xueqi Cheng (2022). Learning node embeddings via summary graphs: a brief theoretical analysis. CoRR, 2022, vol. abs/2207.01189.

Wenjie Feng, Shenghua Liu, Christos Faloutsos, Bryan Hooi, Huawei Shen, Xueqi Cheng (2021). EagleMine: Vision-guided Micro-clusters recognition and collective anomaly detection. Future Generation Computer Systems, 2021, vol. 115, pages 236-250.

Houquan Zhou, Shenghua Liu, Kyuhan Lee, Kijung Shin, Huawei Shen, Xueqi Cheng (2021). DPGS: Degree-Preserving Graph Summarization. Proc. of the SIAM International Conference on Data Mining, SDM, 2021, pages 280-288.

Cite DOI PDF Slides

Xiaobing Sun, Jiabao Zhang, Qiming Zhao, Shenghua Liu, Jinglei Chen, Ruoyu Zhuang, Huawei Shen, Xueqi Cheng (2021). CubeFlow: Money Laundering Detection with Coupled Tensors. Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD, 2021, pages 78-90.

Xiaobing Sun, Jiabao Zhang, Qiming Zhao, Shenghua Liu, Jinglei Chen, Ruoyu Zhuang, Huawei Shen, Xueqi Cheng (2021). CubeFlow: Money Laundering Detection with Coupled Tensors. CoRR, 2021, vol. abs/2103.12411.

Xueqi Cheng, Shenghua Liu, Xiaoqian Sun, Zidong Wang, Houquan Zhou, Yu Shao, Huawei Shen (2021). Combating Emerging Financial Risks in the Big Data Era: A Perspective Review. Fundamental Research, 2021, vol. 1, no. 5, pages 595-606.

Jiabao Zhang, Shenghua Liu, Wenting Hou, Siddharth Bhatia, Huawei Shen, Wenjian Yu, Xueqi Cheng (2021). AugSplicing: Synchronized Behavior Detection in Streaming Tensors. Proc. of the Association for the Advancement of Artificial Intelligence, AAAI, 2021, pages 4653-4661.

Houquan Zhou, Shenghua Liu, Kyuhan Lee, Kijung Shin, Huawei Shen, Xueqi Cheng (2020). Summarizing graphs using the configuration model. CoRR, 2020, vol. abs/2010.09175.

Wenjie Feng, Shenghua Liu, Danai Koutra, Huawei Shen, Xueqi Cheng (2020). SpecGreedy: Unified Dense Subgraph Detection. Proc. of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD, 2020, pages 181-197.

Yiwei Wang, Shenghua Liu, Minji Yoon, Hemank Lamba, Wei Wang, Christos Faloutsos, Bryan Hooi (2020). Provably Robust Node Classification via Low-Pass Message Passing. IEEE International Conference on Data Mining (ICDM), 2020, pages 621-630.

Xiangfeng Li, Shenghua Liu, Zifeng Li, Xiaotian Han, Chuan Shi, Bryan Hooi, He Huang, Xueqi Cheng (2020). FlowScope: Spotting Money Laundering Based on Graphs. Proc. of the Association for the Advancement of Artificial Intelligence, AAAI, 2020, pages 4731-4738.

Xiangyun Ding, Wenjian Yu, Yuyang Xie, Shenghua Liu (2020). Efficient Model-Based Collaborative Filtering with Fast Adaptive PCA. 32nd IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2020, Baltimore, MD, USA, November 9-11, 2020, 2020, pages 955-960.

Xiangyun Ding, Wenjian Yu, Yuyang Xie, Shenghua Liu (2020). Efficient Model-Based Collaborative Filtering with Fast Adaptive PCA. CoRR, 2020, vol. abs/2009.02251.

Jiabao Zhang, Shenghua Liu, Wenting Hou, Siddharth Bhatia, Huawei Shen, Wenjian Yu, Xueqi Cheng (2020). AugSplicing: Synchronized Behavior Detection in Streaming Tensors. CoRR, 2020, vol. abs/2012.02006.

Bryan Hooi, Kijung Shin, Shenghua Liu, Christos Faloutsos (2019). SMF: Drift-Aware Matrix Factorization with Seasonal Patterns. Proc. of the SIAM International Conference on Data Mining, SDM, 2019, pages 621-629.

Jiabao Zhang, Shenghua Liu, Wenjian Yu, Wenjie Feng, Xueqi Cheng (2019). EigenPulse: Detecting Surges in Large Streaming Graphs with Row Augmentation. Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD, 2019, pages 501-513.

Shenghua Liu, Huawei Shen, Houdong Zheng, Xueqi Cheng, Xiangwen Liao (2019). CT LIS: Learning Influences and Susceptibilities through Temporal Behaviors. ACM Transactions on Knowledge Discovery from Data, TKDD, 2019, vol. 13, no. 6, pages 57.

Wenjie Feng, Shenghua Liu, Xueqi Cheng (2019). CatchCore: Catching Hierarchical Dense Subtensor. Proc. of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD, 2019, pages 156-172.

Wenjie Feng, Shenghua Liu, Christos Faloutsos, Bryan Hooi, Huawei Shen, Xueqi Cheng (2019). Beyond Outliers and on to Micro-clusters: Vision-Guided Anomaly Detection. Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD, 2019, pages 541-554.

Bin Zhou, Shenghua Liu, Bryan Hooi, Xueqi Cheng, Jing Ye (2019). BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series. Proc. of the International Joint Conference on Artificial Intelligence, IJCAI, 2019, pages 4433-4439.

Shenghua Liu, Bryan Hooi, Christos Faloutsos (2019). A Contrast Metric for Fraud Detection in Rich Graphs. IEEE Transactions on Knowledge and Data Engineering, TKDE, 2019, vol. 31, no. 12, pages 2235-2248.

Pudi Chen, Shenghua Liu, Chuan Shi, Bryan Hooi, Bai Wang, Xueqi Cheng (2018). NeuCast: Seasonal Neural Forecast of Power Grid Time Series. Proc. of the International Joint Conference on Artificial Intelligence, IJCAI, 2018, pages 3315-3321.

Chuan Shi, Jian Liu, Yiding Zhang, Binbin Hu, Shenghua Liu, Philip S. Yu (2018). MFPR: A Personalized Ranking Recommendation with Multiple Feedback. ACM Transactions on Social Computing, 2018, vol. 1, no. 2, pages 7.

Jian Liu, Chuan Shi, Binbin Hu, Shenghua Liu, Philip S. Yu (2017). Personalized Ranking Recommendation via Integrating Multiple Feedbacks. Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD, 2017, pages 131-143.

Yongqing Wang, Shenghua Liu, Huawei Shen, Jinhua Gao, Xueqi Cheng (2017). Marked Temporal Dynamics Modeling Based on Recurrent Neural Network. Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD, 2017, pages 786-798.

Yongqing Wang, Shenghua Liu, Huawei Shen, Xueqi Cheng (2017). Marked Temporal Dynamics Modeling based on Recurrent Neural Network. CoRR, 2017, vol. abs/1701.03918.

Shenghua Liu, Houdong Zheng, Huawei Shen, Xueqi Cheng, Xiangwen Liao (2017). Learning Concise Representations of Users' Influences through Online Behaviors. Proc. of the International Joint Conference on Artificial Intelligence, IJCAI, 2017, pages 2351-2357.

Shenghua Liu, Bryan Hooi, Christos Faloutsos (2017). HoloScope: Topology-and-Spike Aware Fraud Detection. Proc. of the ACM International Conference on Information and Knowledge Management, CIKM, 2017, pages 1539-1548.

Shenghua Liu, Bryan Hooi, Christos Faloutsos (2017). HoloScope: Topology-and-Spike Aware Fraud Detection. CoRR, 2017, vol. abs/1705.02505.

Wenjie Feng, Shenghua Liu, Christos Faloutsos, Bryan Hooi, Huawei Shen, Xueqi Cheng (2017). EagleMine: Vision-Guided Mining in Large Graphs. CoRR, 2017, vol. abs/1710.08756.

Yongqing Wang, Huawei Shen, Shenghua Liu, Jinhua Gao, Xueqi Cheng (2017). Cascade Dynamics Modeling with Attention-based Recurrent Neural Network. Proc. of the International Joint Conference on Artificial Intelligence, IJCAI, 2017, pages 2985-2991.

Bryan Hooi, Shenghua Liu, Asim Smailagic, Christos Faloutsos (2017). BeatLex: Summarizing and Forecasting Time Series with Patterns. Proc. of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD, 2017, pages 3-19.

Tong Man, Huawei Shen, Shenghua Liu, Xiaolong Jin, Xueqi Cheng (2016). Predict Anchor Links across Social Networks via an Embedding Approach. Proc. of the International Joint Conference on Artificial Intelligence, IJCAI, 2016, pages 1823-1829.

Jinhua Gao, Huawei Shen, Shenghua Liu, Xueqi Cheng (2016). Modeling and Predicting Retweeting Dynamics via a Mixture Process. Proc. of the International World Wide Web Conference, WWW Companion, 2016, pages 33-34.

Shenghua Liu, Houdong Zheng, Huawei Shen, Xiangwen Liao, Xueqi Cheng (2016). Learning Sentimental Influences from Users' Behaviors. CoRR, 2016, vol. abs/1608.03371.

Shenghua Liu, Xueqi Cheng, Fuxin Li, Fangtao Li (2015). TASC: Topic-Adaptive Sentiment Classification on Dynamic Tweets. IEEE Transactions on Knowledge and Data Engineering, TKDE, 2015, vol. 27, no. 6, pages 1696-1709.

Yongqing Wang, Huawei Shen, Shenghua Liu, Xueqi Cheng (2015). Learning User-Specific Latent Influence and Susceptibility from Information Cascades. Proc. of the Association for the Advancement of Artificial Intelligence, AAAI, 2015, pages 477-483.

Fangtao Li, Sheng Wang, Shenghua Liu, Ming Zhang (2014). SUIT: A Supervised User-Item Based Topic Model for Sentiment Analysis. Proc. of the Association for the Advancement of Artificial Intelligence, AAAI, 2014, pages 1636-1642.

Zhankun Huang, Shenghua Liu, Pan Du, Xueqi Cheng (2014). Ranking Tweets with Local and Global Consistency Using Rich Features. Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD, 2014, pages 298-309.

Shenghua Liu, Xueqi Cheng, Fangtao Li (2014). Ranking Tweets by Labeled and Collaboratively Selected Pairs with Transitive Closure. Proc. of the Association for the Advancement of Artificial Intelligence, AAAI, 2014, pages 1235-1241.

Xueqi Cheng, Jiafeng Guo, Shenghua Liu, Yanfeng Wang, Xiaohui Yan (2013). Learning Topics in Short Texts by Non-negative Matrix Factorization on Term Correlation Matrix. Proc. of the SIAM International Conference on Data Mining, SDM, 2013, pages 749-757.

Shenghua Liu, Wenjun Zhu, Ning Xu, Fangtao Li, Xueqi Cheng, Yue Liu, Yuanzhuo Wang (2013). Co-training and visualizing sentiment evolvement for tweet events. Proc. of the International World Wide Web Conference, WWW Companion, 2013, pages 105-106.

Shenghua Liu, Fuxin Li, Fangtao Li, Xueqi Cheng, Huawei Shen (2013). Adaptive co-training SVM for sentiment classification on tweets. Proc. of the ACM International Conference on Information and Knowledge Management, CIKM, 2013, pages 2079-2088.

Xiaohui Yan, Jiafeng Guo, Shenghua Liu, Xueqi Cheng, Yanfeng Wang (2012). Clustering short text using Ncut-weighted non-negative matrix factorization. Proc. of the ACM International Conference on Information and Knowledge Management, CIKM Short, 2012, pages 2259-2262.

Shenghua Liu, Yuchun Ma, Xianlong Hong, Yu Wang (2010). Simultaneous slack budgeting and retiming for synchronous circuits optimization. Proc. of the Asia and South Pacific Design Automation Conference, ASP-DAC, 2010, pages 49-54.

Shenghua Liu, Guoqiang Chen, Tom Tong Jing, Lei He, Robi Dutta, Xianlong Hong (2010). Effective congestion reduction for IC package substrate routing. IEEE Transactions on Design Automation of Electronic Systems, TODAES, 2010, vol. 15, no. 3.

Shenghua Liu, Guoqiang Chen, Tom Tong Jing, Lei He, Tianpei Zhang, Robi Dutta, Xianlong Hong (2009). Substrate Topological Routing for High-Density Packages. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, TCAD, 2009, vol. 28, no. 2, pages 207-216.

Shenghua Liu, Guoqiang Chen, Tom Tong Jing, Lei He, Robi Dutta, Xianlong Hong (2009). Diffusion-driven congestion reduction for substrate topological routing. International Symposium on Physical Design (ISPD SIGDA), 2009, pages 175-180.

Shenghua Liu, Guoqiang Chen, Tom Tong Jing, Lei He, Tianpei Zhang, Robi Dutta, Xianlong Hong (2008). Topological routing to maximize routability for package substrate. Proc. of the Design Automation Conference, DAC, 2008, pages 566-569.

Shenghua Liu, Xianlong Hong, Tong Jing, Jingyu Xu (2006). FREe: a fast routability estimator. IEEE International Conference on Communications, Circuits and Systems (ICCCAS), 2006, pages 2454-2458.