Honghao Liu

Publications

Research & writing

Work on trustworthy reasoning, privacy-preserving language models, neural speech decoding, and scientific computing.

Google Scholar ↗

Publications

6 works
  1. ACL 2026

    Conflicts Make Large Reasoning Models Vulnerable to Attacks

    H. Liu, C. Xu, X. Jiang, C. Yang, S. Yin, Z. Ma, L. Ni, and J. Guo.

    Findings of ACL 2026 · pp. 9509–9531 · San Diego, California, USA

    Paper ↗
  2. ACL 2026

    Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning

    C. Yang, X. Lin, X. Wu, C. Xu, X. Jiang, H. Liu, H. Xiong, and J. Guo.

    Findings of ACL 2026 · pp. 6656–6671 · San Diego, California, USA

  3. EACL 2026

    Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs

    H. Liu, X. Jiang, C. Xu, C. Yang, Y. Cheng, L. Ni, and J. Guo.

    Findings of EACL 2026 · pp. 408–425 · Rabat, Morocco

    Paper ↗
  4. Innovation

    A Survey on LLM-as-a-Judge

    J. Gu, X. Jiang, Z. Shi, H. Tan, X. Zhai, C. Xu, W. Li, Y. Shen, S. Ma, H. Liu, S. Wang, K. Zhang, Y. Wang, W. Gao, L. Ni, and J. Guo.

    The Innovation · DOI: 10.1016/j.xinn.2025.101253

    Paper ↗
  5. IJCAI Workshop

    Decoding Multi-Talker Speech from EEG Signals

    H. Liu, K. Li, Q. Zhou, Q. Wang, J. Sun, Z. Huang, and J. Li.

    IJCAI Workshop on Human Brain and Artificial Intelligence · Abstract · Jeju, South Korea

  6. e-Science

    Efficient Radio Interferometric Imaging on the GPU

    H. Liu, Q. Luo, and F. Wang.

    IEEE 18th International Conference on e-Science · Salt Lake City, UT, USA · DOI: 10.1109/eScience55777.2022.00024

    Paper ↗