About me

Welcome to my homepage! I am Weihang Su (苏炜航), a fourth-year PhD student at the Department of Computer Science and Technology, Tsinghua University, where I am fortunate to be advised by Prof. Yiqun Liu and Assoc. Prof. Qingyao Ai.

My research focuses on leveraging Large Language Models (LLMs) to better fulfill users’ complex information needs. My current research interests include:

• Retrieval-Augmented Generation (RAG) & AI Agents
• Hallucination Detection and Mitigation for LLMs
• AI for Legal Applications

My research at the intersection of Information Retrieval and Large Language Models has achieved both significant academic recognition and broad impact. Recent highlights of my works include receiving the SIGIR 2024 Best Paper Award 🏆, and my work on Parametric RAG is currently the most cited paper at SIGIR 2025 📈 (as of Feb 2026, Google Scholar). Beyond publications, I actively serve the research community as a PC member or reviewer for top-tier venues (e.g., NeurIPS, ICML, ICLR, ACL, SIGIR) and have been invited to deliver tutorials at flagship conferences (e.g., SIGIR 2025, SIGIR-AP 2025) on Dynamic and Parametric RAG, serving as the lead presenter.

My academic work is also closely connected to industrial practice. Since October 2025, I have been working as a research intern at ByteDance (TikTok), focusing on the development of advanced AI Agents. By exploring the automated construction of specialized agents and Agent Skills for agentic systems, I aim to bridge the gap between cutting-edge LLM research and scalable, real-world applications.

I am also highly passionate about mentoring undergraduate students. I have had the privilege of collaborating with talented undergraduates, successfully co-authoring high-impact papers at premier conferences and journals (e.g., ACL, SIGIR, EMNLP, TOIS, AAAI, The Web Conference).

If you are an undergraduate student interested in my research areas and driven to publish high-quality work, you are more than welcome to apply for an internship with the THUIR group through official channels, or contact me directly (WeChat ID: rdfzswh) to embark on meaningful research together!

News

• Our Paper GPRF has been accepted at WebConf 2026 Conference! Congratulations to Yiteng!

• Our SIGIR-AP 2025 tutorial on Dynamic and Parametric RAG has been accepted! Welcome to join us in Xi’an, China, on December 7th! More information at: This Webpage and SIGIR-AP 2025 Official Website.

• Our Paper AutoPRE has been accepted at AAAI 2026 Main Conference! After a long journey since June 2024, it’s finally accepted. Congratulations to Junjie!
• Our Paper RACE has been selected for an Oral presentation at AAAI 2026! Congratulations to Changyue!
• Our Paper EditCot has been accepted at EMNLP 2025 Main Conference!
• Our Paper SDE has been accepted at EMNLP 2025 Main Conference! Congratulations to Yichen!
• My first-authored Long Paper Caseformer has been accepted at TOIS 2025!
• Our SIGIR 2025 tutorial on Dynamic and Parametric RAG has been accepted! More information at: https://sites.google.com/view/sigir2025-tutorial-dprag/home-page
• Our Paper DecKER, has been accepted at Findings of ACL 2025! Congratulations to Changyue!
• My first-authored Tutorial on RAG has been accepted at SIGIR 2025!
• Our Paper RbFT has been accepted at SIGIR 2025! Congratulations to Yiteng!
• My first-authored Long Paper JuDGE has been accepted at SIGIR 2025!
• My first-authored Long Paper Parametric RAG has been accepted at SIGIR 2025!
• My first-authored Long Paper DRAD has been accepted at SIGIR-AP 2024!
• My first-authored Long Paper STARD has been accepted at EMNLP 2024!
• Our paper “Scaling Laws for Dense Retrieval” received the SIGIR Best Paper Award!
• My first-authored paper “DRAGIN” has been selected for an Oral presentation at ACL! (Top 2.6% in submissions, top 6.8% in accepted papers)
• My first-authored Long Paper DRAGIN has been accepted at ACL 2024 Main Conference!
• My first-authored Long Paper MIND has been accepted at Findings of ACL 2024!
• My first-authored Long Paper Wikiformer has been accepted at AAAI 2024!
• Our team participated in COLIEE 2023 and won the championship! Here is the link to our Technical Report: https://arxiv.org/abs/2304.12650
• We participated in the WSDM Cup 2023 and won silver medals in two tasks! Here is the news report: https://www.cs.tsinghua.edu.cn/info/1088/5286.htm

Selected Awards

• WizardQuant Scholarship, Top 2 in the Department of CST, Tsinghua University, 2025
• ICLR Notable Reviewer
• China Association for Science and Technology’s Young Talents Project, Ph.D. Program (中国科协青年人才托举工程)
• National Scholarship (国家奖学金), Top 4 in the Department of CST, Tsinghua University, 2024
• SIGIR 2024 Best Paper Award
• ACL 2024 Oral
• Winner of the Language and Intelligence Challenge (LIC) Contest (4 winners in the world. Ranked 0.3% among all teams).
• Beijing Outstanding Undergraduate (2022)

Publications

Link to Google Scholar

The titles of my first-author papers are in bold (excluding co-first where the ranking is not first).

Paper Under Submission

• SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation
  Weihang Su, Anzhe Xie, Qingyao Ai, Jianming Long, Jiaxin Mao, Ziyi Ye, Yiqun Liu
  (Long Paper) Paper Code and Dataset

• Towards Unification of Hallucination Detection and Fact Verification for Large Language Models
  Weihang Su, Jianming Long, Changyue Wang, Shiyu Lin, Jingyan Xu, Ziyi Ye, Qingyao Ai, Yiqun Liu
  (Long Paper) Paper Code and Dataset

Year 2026

• Generalized Pseudo-Relevance Feedback
  Yiteng Tu, Weihang Su, Yujia Zhou, Yiqun Liu, Fen Lin, Qin Liu, Qingyao Ai
  Webconf 2026 (Long Paper, CCF-A, THU-A)
  Paper

• Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models
  Changyue Wang, Weihang Su, Qingyao Ai, Yiqun Liu
  AAAI 2026 Main Oral (Long Paper, CCF-A, THU-A)
  Paper Code

• An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation
  Junjie Chen, Weihang Su, Zhumin Chu, Haitao Li, Qinyao Ai, Yiqun Liu, Min Zhang, Shaoping Ma
  AAAI 2026 Main (Long Paper, CCF-A, THU-A)
  Paper Code

Year 2025

• Augmenting Multi-Agent Communication with State Delta Trajectory
  Yichen Tang, Weihang Su, Yujia Zhou, Yiqun Liu, Min Zhang, Shaoping Ma, Qingyao Ai
  EMNLP 2025 Main (Long, CCF-B, THU-A) Paper Code

• Knowledge Editing through Chain-of-Thought
  Changyue Wang, Weihang Su, Qingyao Ai, Yiqun Liu
  EMNLP 2025 Main (Long, CCF-B, THU-A) Paper Code

• Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
  Changyue Wang, Weihang Su, Qingyao Ai, Yujia Zhou, Yiqun Liu
  ACL 2025 Findings (Long, CCF-A, THU-A) Paper Code

• Dynamic and Parametric Retrieval-Augmented Generation
  Weihang Su, Qingyao Ai, Jingtao Zhan, Qian Dong, Yiqun Liu
  SIGIR 2025 (Tutorial, CCF-A, THU-A) Official Website Tutorial Proposal Paper

• Parametric Retrieval Augmented Generation
  Weihang Su, Yichen Tang, Qingyao Ai, Junxi Yan, Changyue Wang, Hongning Wang, Ziyi Ye, Yujia Zhou, Yiqun Liu
  SIGIR 2025 (Long Paper, CCF-A, THU-A) Paper Code

• JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System
  Weihang Su, Baoqing Yue, Qingyao Ai, Yiran Hu, Jiaqi Li, Changyue Wang, Kaiyuan Zhang, Yueyue Wu, Yiqun Liu
  SIGIR 2025 (Long Paper, CCF-A, THU-A) Paper Code and Dataset

• Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects
  Yiteng Tu, Weihang Su, Yujia Zhou, Yiqun Liu, Qingyao Ai
  SIGIR 2025 (Long Paper, CCF-A, THU-A) Paper Code

• Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions.
  Weihang Su, Qingyao Ai, Yueyue Wu, Anzhe Xie, Changyue Wang, Yixiao Ma, Haitao Li, Zhijing Wu, Yiqun Liu, Min Zhang.
  ACM Transactions on Information Systems
  TOIS 2025 (Long Paper, CCF-A, THU-A)

• DecoupledRAG: An Efficient and Effective Retrieval Augmented Generation Framework via Cross Attention.
  Qian Dong, Qingyao Ai, Hongning Wang, Yiding Liu, Haitao Li, Weihang Su, Yiqun Liu, Tat-Seng Chua, Shaoping Ma.
  ACM Transactions on Information Systems
  WWW 2025 (Long Paper, CCF-A, THU-A)

Year 2024

• Mitigating Entity-Level Hallucinations in Large Language Models
  Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, Yiqun Liu
  International ACM SIGIR Conference on Information Retrieval in the Asia Pacific
  SIGIR-AP 2024 (Long Paper) Paper Code

• LeKUBE: A Legal Knowledge Update BEnchmark
  Changyue Wang, Weihang Su, Hu Yiran, Qingyao Ai, Yueyue Wu, Cheng Luo, Yiqun Liu, Min Zhang, Shaoping Ma
  International ACM SIGIR Conference on Information Retrieval in the Asia Pacific
  SIGIR-AP 2024 (Long Paper) Paper Code

• STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals
  Weihang Su, Yiran Hu, Anzhe Xie, Qingyao Ai, Zibing Que, Yun Liu, Weixing Shen, Yiqun LIU
  The 2024 Conference on Empirical Methods in Natural Language Processing
  EMNLP 2024 Findings (Long Paper, CCF-B, THU-A) Paper Code

• DRAGIN: Dynamic Retrieval Augmented Generation based on the Real-time Information Needs of Large Language Models
  Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, Yiqun Liu.
  Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.
  ACL 2024 Main Oral (Long Paper, CCF-A, THU-A)
  [Paper] Code

• Unsupervised real-time hallucination detection based on the internal states of large language models
  Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, Yiqun Liu.
  Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.
  ACL 2024 Findings (Long Paper, CCF-A, THU-A)
  Paper Code

• Scaling Laws For Dense Retrieval.
  Yan Fang, Jingtao Zhan, Qingyao Ai, Jiaxin Mao, Weihang Su, Jia Chen and Yiqun Liu.
  The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval
  SIGIR 2024 Best Paper Award (Long Paper, CCF-A, THU-A)

• Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval.
  Weihang Su, Qingyao Ai, Xiangsheng Li, Jia Chen, Yiqun Liu, Xiaolong Wu and Shengluan Hou.
  The 38th Annual AAAI Conference on Artificial Intelligence
  AAAI 2024 (Long Paper, CCF-A, THU-A)
  Paper Code

• Relevance Feedback with Brain Signals.
  Ziyi Ye, Xiaohui Xie, Qingyao Ai, Yiqun Liu, Zhihong Wang, Weihang Su and Min Zhang.
  ACM Transactions on Information Systems
  TOIS 2024 (Long Paper, CCF-A, THU-A)

Before 2024

• CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding.
  Yixiao Ma, Yueyue Wu, Weihang Su, Qingyao Ai, Yiqun Liu.
  The 2023 Conference on Empirical Methods in Natural Language Processing
  EMNLP 2023 Main (Long Paper, CCF-B, THU-A)

• THUIR2 at NTCIR-16 Session Search (SS) Task
  Weihang Su, Xiangsheng Li, Yiqun Liu, Min Zhang, Shaoping Ma
  NII Testbeds and Community for Information access Research Project
  NTCIR 2022

• Web Search via an Efficient and Effective Brain-Machine Interface.
  Xuesong Chen, Ziyi Ye, Xiaohui Xie, Yiqun Liu, Xiaorong Gao, Weihang Su, Shuqi Zhu, Yike Sun, Min Zhang, and Shaoping Ma.
  The 15th ACM International Conference on Web Search and Data Mining.
  (WSDM 2022) (Demo Paper, CCF-B, THU-A)

• Trade or trick? detecting and characterizing scam tokens on uniswap decentralized exchange
  Pengcheng Xia, Haoyu Wang, Bingyu Gao, Weihang Su, Zhou Yu, Xiapu Luo, Chao Zhang, Xusheng Xiao, Guoai Xu
  International Conference on Measurement and Modeling of Computer Systems
  (SIGMETRICS 2022) (Long Paper, CCF-B, THU-A)

Vistors of this Site