me2.jpg

Hongfu Liu (刘洪甫)

Contact: liu (dot) hongfu [at] u (dot) nus (dot) edu

Hi! I am a fourth-year Ph.D. student in SMC Lab at National University of Singapore. I am fortunate to be advised by Prof. Ye Wang. Previously, I obtained my Bachelor’s degree in Computer Science at Zhejiang University.

I am broadly interested in machine learning for NLP, Speech, Multimodality topics. Currently, I focus more on improving large language/multimodal foundation models from two directions: (1) Audio-Language: designing data-efficient approaches for better language and speech understanding; (2) Trustworthy: investigating the risks and enhancing the robustness and safety.

I am always open to collaborations and feel free to reach out if you share similar interests!


News

Sep, 2024 Our paper “Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models” and “Advancing Test-Time Adaptation in Wild Acoustic Test Settings” got accepted to EMNLP 2024 (two Main)! Many thanks to all my collaborators! Can’t wait to meet you in Miami! :sunny:
Aug, 2024 Our paper “Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations” received the Area Chair Award at ACL 2024! Congrats to Yisong and the whole team! :fire:
May, 2024 Our paper “Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations” and “Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset” got accepted to ACL 2024 (one Main and one Finding)! Congrats to all co-authors! :smile:
Oct, 2023 Our paper “Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning” got accepted to the EMNLP 2023 (Finding)! Thanks to my advisor!
May, 2023 Our paper “Zero-Shot Automatic Pronunciation Assessment” got accepted to Interspeech 2023! Thanks to all collaborators!
Nov, 2022 Our paper “Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation” got accepted to NeurIPS 2022! Congrats to all co-authors!
May, 2022 I passed my Ph.D. Qualifying Examination (PQE) and became a Ph.D. candidate! Many thanks to my advisor! :tada:
May, 2021 Our paper “STRODE: Stochastic Boundary Ordinary Differential Equation” got accepted to ICML 2021! Thanks to all collaborators!

Selected Publications

(*) denotes equal contribution

  1. PreprintOral
    On Calibration of LLM-based Guard Models for Reliable Content Moderation
    Hongfu Liu, Hengguan Huang, Hao Wang, Xiangming Gu, and Ye Wang
    In NeurIPS Safe Generative AI workshop, 2024
  2. EMNLP
    Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models
    Hongfu Liu*, Yuxi Xie*, Ye Wang, and Michael Shieh
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  3. EMNLPOral
    Advancing Test-Time Adaptation in Wild Acoustic Test Settings
    Hongfu Liu, Hengguan Huang, and Ye Wang
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  4. ACLOral
    Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations
    Yisong Miao, Hongfu Liu, Wenqiang Lei, Nancy F. Chen, and Min-Yen Kan
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2024
    Area Chair Award
  5. ACL Findings
    Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset
    Hengguan Huang*, Songtao Wang*, Hongfu Liu, Hao Wang, and Ye Wang
    In Findings of Annual Meeting of the Association for Computational Linguistics (ACL), 2024
  6. EMNLP Findings
    Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning
    Hongfu Liu, and Ye Wang
    In Findings of Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
  7. Interspeech
    Zero-Shot Automatic Pronunciation Assessment
    Hongfu Liu, Mingqian Shi, and Ye Wang
    In Interspeech, 2023
  8. NeurIPS
    Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation
    Hengguan Huang, Xiangming Gu, Hao Wang, Chang Xiao, Hongfu Liu, and Ye Wang
    In Advances in Neural Information Processing Systems (NeurIPS), 2022
  9. ICML
    STRODE: Stochastic Boundary Ordinary Differential Equation
    Hengguan Huang, Hongfu Liu, Hao Wang, Chang Xiao, and Ye Wang
    In International Conference on Machine Learning (ICML), 2021


Academic Services

  • Conference Reviewers:

    ACL Rolling Review (2023&2024), NeurIPS (2024), ICLR (2024&2025), IJCAI (2024)



Teaching

  • CS4347: Sound and Music Computing (2022 Spring / 2022 Fall)

  • CS5242: Neural Networks and Deep Learning (2021 Fall / 2023 Spring)



MISC

  • I am a big fan of live music and attend numerous concerts every year, enjoying a wide variety of music genres. My favorate genre is R&B. :musical_note: :notes: :musical_score: :musical_keyboard:

  • I also enjoy traveling and exploring different cultures, especially experiencing diverse cuisines from around the world.