俞蔚捷
学系：人工智能系
欢迎全年级同学加入Language and Information Technology (LIT)小组，一起做有意义、有影响力的研究，详情请见https://ruc-wjyu.github.io/
联系方式：邮箱：yu@uibe.edu.cn 办公电话：010-64491734
研究兴趣：我的研究兴趣为信息检索、大语言模型、智能体等，主要关注法律智能、推荐系统、AI4SocialScience等领域，欢迎对相关研究感兴趣且具备编程基础的同学与我联系。
教育背景：
2018-2023，中国人民大学，信息学院，博士
2015-2018，中国科学技术大学，软件学院，硕士
2010-2014，辽宁大学，信息学院，学士
工作经历：
2026-，对外经济贸易大学，人工智能与数据科学学院，副教授（破格晋升）
2023-2025，对外经济贸易大学，人工智能与数据科学学院，助理教授
学术发表：
2026：
Zhang, K., Yu, W*., Sun, Z., Qin, W., Xu, J., & Wen, J. R. (2026). Empowering open-domain LLMs for legal document correction via legal knowledge integration and decoding constraints. Information Processing & Management , 63 (6), 104703.
Wang, H., Shang, Y., Sun, Z., Yu, W., Zhang, X., & Xu, J. (2026). Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm. ICML 2026.
Zhang, K., Yu, W., & Xu, J. (2026, May). Tuning-Free Fidelity-Constrained Decoding for Faithful Legal Reasoning with Open-Domain Large Language Models. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 18672-18676). IEEE.
Shen, C., Zhan, Y., Yu, W., Zhang, X., & Xu, J. (2026). Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations. ACM Transactions on Information Systems , 44 (3), 1-30.
Shen, C., Shi, T., Yu, W., Zhang, X., & Xu, J. (2026). Bringing Model Editing to Generative Recommendation in Cold-Start Scenarios. SIGIR 2026.
Sun, Z., Wang, Q., Yu, W., Yang, J., Lu, H., & Xu, J. (2026). Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience. SIGIR 2026.
Zhang, K., Sun, Z., Yu, W., Zang, X., Zheng, K., Song, Y., ... & Xu, J. (2025). Qe-rag: A robust retrieval-augmented generation benchmark for query entry errors. SIGIR 2026 Resource paper.
Sun, Z., Zhan, Y., Shen, C., Yu, W., Zhang, X., He, M., & Xu, J. (2026). When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs. ACL 2026 Findings.
Chen, X., Li, X., Sun, Z., & Yu, W*. (2025). Beyond high-entropy exploration: Correctness-aware low-entropy segment-based advantage shaping for reasoning llms. ACL 2026 Findings.
2025:
Shi, T., Yu, W.*, Zhang, X., He, M., Fan, J., & Xu, J. (2025, November). Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (pp. 2685-2695).
Zhang, K., Shi, T., Yu, W*., & Xu, J. (2025, November). Prlm: Learning explicit reasoning for personalized rag via contrastive reward optimization. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (pp. 5484-5488).
Zhang, K., Yu, W*., Sun, Z., & Xu, J. (2025, November). Syler: A framework for explicit syllogistic legal reasoning in large language models. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (pp. 4117-4127).
Qin, W., Xu, Y., Yu, W*., Shi, T., Shen, C., He, M., ... & Xu, J. (2025, November). Similarity= Value? Consultation Value-Assessment and Alignment for Personalized Search. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 9850-9863).
Zhang, K., Xie, G., Yu, W.*, Xu, M., Tang, X., Li, Y., & Xu, J. (2025). Legal mathematical reasoning with llms: Procedural alignment through two-stage reinforcement learning. EMNLP 2025 Findings.
Zhang, K., Yang, H., Tang, X., Yu, W.*, & Xu, J. (2024). Beyond guilt: Legal judgment prediction with trichotomous reasoning. EMNLP 2025 Findings.
Qin, W., Xu, Y., Yu, W.*, Shen, C., He, M., Fan, J., ... & Xu, J. (2025, July). Maps: Motivation-aware personalized search via llm-driven consultation alignment. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 3039-3051).
Zhang, K., Yu, W.*, Dai, S., & Xu, J. (2025, July). Citalaw: Enhancing llm with citations in legal domain. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 11183-11196).
Sun, Z., Zang, X., Zheng, K., Xu, J., Zhang, X., Yu, W., ... & Li, H. (2025, May). Redeep: Detecting hallucination in retrieval-augmented generation via mechanistic interpretability. In International Conference on Learning Representations (Vol. 2025, pp. 50250-50279).
Qin, W., Xu, Y., Yu, W*., Shen, C., Zhang, X., He, M., ... & Xu, J. (2025, September). More: A mixture of reflectors framework for large language model-based sequential recommendation. In Proceedings of the Nineteenth ACM Conference on Recommender Systems (pp. 299-308).
Qin, W., Yu, W*., Zhang, K., Zhao, H., Xu, J., & Wen, J. R. (2025). Uncertainty-aware evidential learning for legal case retrieval with noisy correspondence. Information Sciences , 702 , 121915.
Shen, C., Zhao, J., Zhang, X., Yu, W., He, M., & Fan, J. (2025, September). Paragon: Parameter Generation for Controllable Multi-Task Recommendation. In Proceedings of the Nineteenth ACM Conference on Recommender Systems (pp. 370-380).
Sun, Z., Wang, Q., Yu, W., Zang, X., Zheng, K., Xu, J., ... & Li, H. (2025, July). Rearter: Retrieval-augmented reasoning with trustworthy process rewarding. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1251-1261).
研究项目：
主持国家自然科学基金青C项目“面向法律场景的可信检索增强推理方法研究”。
主持校级课题“面向中文司法场景的可信类案检索研究”。
主持校级课题“面向司法类案检索的生成式人工智能技术研究”。
主持企业横向课题“双语环境下司法类案检索算法的研究与应用”。
参与国家重点研发计划“面向多元化纠纷化解的智能法律助理和类案分析系统关键技术研究”。
参与国家自然科学基金面上项目“基于强化学习的信息检索排序模型研究”。
获奖情况：
指导学生团队获得2026计算机程序设计大赛北京市三等奖。
指导学生团队获得2025挑战杯北京市二等奖两次。
获得中国人民大学2024优秀博士论文奖。
学术服务：
中国中文信息学会青年工作委员会委员、信息检索专委会委员、大模型专委会委员。
教授课程：
本科生课程：自然语言处理、数据结构与算法分析、Python与大数据分析、人工智能素养与实践
研究生课程：人工智能+X