Publication

Selected Publications (Full publist on google scholar)

Please read my newest preprints (at the bottom of this page) to see my latest research focus.


Conference & Journal

2025

  1. ACL
    Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study over Open-ended Question Answering
    Yuan Sui, Yufei He,  Zifeng Ding, and Bryan Hooi
    The 63rd Annual Meeting of the Association for Computational Linguistics 2025
    arXiv
  2. ACL
    BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
    Ercong Nie, Bo Shao, Mingyang Wang,  Zifeng Ding, Helmut Schmid, and Hinrich Schütze
    The 63rd Annual Meeting of the Association for Computational Linguistics 2025
    arXiv
  3. ACL
    Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings
    Yuqicheng Zhu, Daniel Hernández, Yuan He,  Zifeng Ding, Bo Xiong, Evgeny Kharlamov, and Steffen Staab
    Findings of the Association for Computational Linguistics: ACL 2025
  4. TMLR
    DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models
    Zifeng Ding, Yifeng Li, Yuan He, Antonio Norelli, Jingcheng Wu, Volker Tresp, Michael Bronstein, and Yunpu Ma
    Transactions on Machine Learning Research 2025
    arXiv

2024

  1. EMNLP
    Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs
    Zifeng Ding, Jingcheng Wu, Jingpei Wu, Yan Xia, Bo Xiong, and Volker Tresp
    Findings of the Association for Computational Linguistics: EMNLP 2024
    arXiv
  2. COLM
    Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
    Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue,  Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, and Jindong Gu
    First Conference on Language Modeling 2024
    arXiv
  3. NAACL
    zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
    Zifeng Ding, Heling Cai, Jingpei Wu, Yunpu Ma, Ruotong Liao, Bo Xiong, and Volker Tresp
    Annual Conference of the North American Chapter of the Association for Computational Linguistics 2024
    arXiv
  4. CVPR
    Text2loc: 3d point cloud localization from natural language
    Yan Xia, Letian Shi,  Zifeng Ding, Joao F Henriques, and Daniel Cremers
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
    arXiv
  5. SeTLLM@ICLR
    Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
    Shuo Chen, Zhen Han, Bailan He,  Zifeng Ding, Wenqian Yu, Philip Torr, Volker Tresp, and Jindong Gu
    2nd Differentiable Almost Everything Workshop at the 41st International Conference on Machine Learning 2024
    arXiv
  6. ESWC
    Critical Path Identification in Supply Chain Knowledge Graphs with Large Language Models
    Yaomengxi Han,  Zifeng Ding, Yushan Liu, Bailan He, and Volker Tresp
    Extended Semantic Web Conference (Poster & Demo Track) 2024

2023

  1. ISWC
    ForecastTKGQuestions: A Benchmark for Temporal Question Answering and Forecasting over Temporal Knowledge Graphs
    Zifeng Ding, Zongyue Li, Ruoxia Qi, Jingpei Wu, Bailan He, Yunpu Ma, Zhao Meng, Shuo Chen, Ruotong Liao, Zhen Han, and Volker Tresp
    International Semantic Web Conference 2023
    arXiv
  2. ECML PKDD
    Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs using Confidence-Augmented Reinforcement Learning
    Zifeng Ding, Jingpei Wu, Zongyue Li, Yunpu Ma, and Volker Tresp
    European Conference on Machine Learning and Knowledge Discovery in Databases 2023
    arXiv
  3. IJCNN
    Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction
    Zifeng Ding, Bailan He, Yunpu Ma, Zhen Han, and Volker Tresp
    International Joint Conference on Neural Networks 2023
    arXiv
  4. ACL
    ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations
    Zhen Han, Ruotong Liao, Jindong Gu, Yao Zhang,  Zifeng Ding, Yujia Gu, Heinz Köppl, Hinrich Schütze, and Volker Tresp
    Findings of the Association for Computational Linguistics: ACL 2023
    arXiv

2022

  1. AKBC
    Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information
    Zifeng Ding, Jingpei Wu, Bailan He, Yunpu Ma, Zhen Han, and Volker Tresp
    Automated Knowledge Base Construction 2022
    arXiv
  2. SPNLP@ACL
    TempCaps: A Capsule Network-based Embedding Model for Temporal Knowledge Graph Completion
    Guirong Fu, Zhao Meng, Zhen Han,  Zifeng Ding, Yunpu Ma, Matthias Schubert, Volker Tresp, and Roger Wattenhofer
    The Sixth Workshop on Structured Prediction for NLP 2022
  3. TGL@NeurIPS
    A Simple But Powerful Graph Encoder for Temporal Knowledge Graph Completion
    Zifeng Ding, Yunpu Ma, Bailan He, and Volker Tresp
    NeurIPS 2022 Temporal Graph Learning Workshop 2022
    arXiv

2021

  1. EMNLP
    Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs
    Zhen Han,  Zifeng Ding, Yunpu Ma, Yujia Gu, and Volker Tresp
    Conference on Empirical Methods in Natural Language Processing 2021
    arXiv

Preprint

2025

  1. arXiv
    TCP: a Benchmark for Temporal Constraint-Based Planning
    Zifeng Ding, Sikuan Yan, Zhangdie Yuan, Xianglong Hu, Fangru Lin, and Andreas Vlachos
    arXiv preprint 2025
    arXiv
  2. arXiv
    Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
    Weixing Wang,  Zifeng Ding, Jindong Gu, Rui Cao, Christoph Meinel, Gerard Melo, and Haojin Yang
    arXiv preprint 2025
    arXiv
  3. arXiv
    AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web
    Rui Cao,  Zifeng Ding, Zhijiang Guo, Michael Schlichtkrull, and Andreas Vlachos
    arXiv preprint 2025
    arXiv
  4. arXiv
    Supposedly Equivalent Facts That Aren’t? Entity Frequency in Pre-training Induces Asymmetry in LLMs
    Yuan He, Bailan He,  Zifeng Ding, Alisia Lupidi, Yuqicheng Zhu, Shuo Chen, Caiqi Zhang, Jiaoyan Chen, Yunpu Ma, Volker Tresp, and Ian Horrocks
    arXiv preprint 2025
    arXiv
  5. arXiv
    The Future Outcome Reasoning and Confidence Assessment Benchmark
    Zhangdie Yuan,  Zifeng Ding, and Andreas Vlachos
    arXiv preprint 2025
    arXiv

2024

  1. arXiv
    PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
    Yilun Liu, Yunpu Ma, Shuo Chen,  Zifeng Ding, Bailan He, Zhen Han, and Volker Tresp
    arXiv preprint 2024
    arXiv