靳浩然, Haoran Jin

靳浩然, Haoran Jin

he/his

Computer Science and Technology Ph.D student

About Me

Haoran Jin (靳浩然) is a first-year Ph.D. student at the School of Computer Science and Technology, University of Science and Technology of China (USTC). He received his B.Eng. degree in Computer Science and Technology from USTC in 2023 and continued his research as a Master’s student (2023–2025) before transitioning to the Ph.D. program in May 2025.

His research focuses on Interpretability and Alignment of Large Language Models (LLMs), with an emphasis on enhancing the transparency, controllability, and safety of AI systems. He is particularly interested in activation engineering, mechanistic interpretability, and unsupervised interpretability paradigms.

Recent Updates

  • 2025.05.15: Our work Internal Value Alignment in Large Language Models through Controlled Value Vector Activation has been accepted by ACL 2025 Main Conference! 🌟😉
  • 2024.09.24: Our work Evaluating Readability and Faithfulness of Concept-based Explanations (co-first authored with Meng Li) has been accepted by EMNLP 2024 Main Conference! ✨😆

Educations

University of Science and Technology of China (USTC)

  • Ph.D. in Computer Science and Technology (Expected 2025.9 – Present)
    School of Computer Science and Technology
    • Transferred from Master’s to Ph.D. with a successive postgraduate-doctoral Program in May 2025.

  • M.Eng. in Computer Science and Technology (2023.9 – 2025.5)
    School of Computer Science and Technology

  • B.Eng. in Computer Science and Technology (2019.9 – 2023.6)
    School of Computer Science and Technology

Publications

Haoran Jin, Meng Li, Xiting Wang*, Zhihao Xu, Minlie Huang, Yantao Jia, Defu Lian*. Internal Value Alignment in Large Language Models through Controlled Value Vector Activation. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025 Main Conference), accepted, 2025. [paper] [code]

Meng Li†, Haoran Jin†, Ruixuan Huang, Zhihao Xu, Defu Lian, Zijia Lin, Di Zhang, and Xiting Wang*. Evaluating Readability and Faithfulness of Concept-based Explanations. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main Conference), pages 607–625, 2024. [paper] [code]

Qi Liu, Xuyang Hou, Defu Lian*, Zhe Wang, Haoran Jin, Jia Cheng, Jun Lei. AT4CTR: auxiliary match tasks for enhancing click-through rate prediction Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI 2024). Vol. 38, No. 8, 2024. [paper] [code]

Defu Lian*, Xu Huang, Xiaolong Chen, Jin Chen, Xingmei Wang, Yankai Wang, Haoran Jin, Rui Fan, Zheng Liu, Le Wu, Enhong Chen. RecStudio: Towards a Highly-Modularized Recommender System. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023), pp. 2890-2900, 2023. [paper] [code]

Awards

  • Gold Medal for Outstanding Students 2022.10

  • CSEDM Competition 2022.05

    Educational Data Mining in Computer Science Education [results]

    • 1st Place in Exercise Performance Prediction Track

    • 2nd Place in Final Grade Prediction Track

  • Huawei Scholarship 2021.10

    Ranked 10th out of 175 (top 6%) in comprehensive evaluation