About me

I am now a third year master student in THUIR, Department of Computer Science and Technology, Tsinghua University. My supervisor is Prof. Yiqun Liu.

My research focuses on the following areas:

LLM4Legal: Focused on the in-depth application and optimization of LLMs in the legal domain. This includes:

  • Vertical Knowledge Injection
    Exploring efficient methods (e.g., post-training) to incorporate domain-specific legal knowledge into LLMs, enhancing their performance in specialized legal tasks.
  • 📚 Domain-Specific Data Synthesis
    Developing tailored training techniques for the legal field, leveraging self-play to generate structured and domain-compliant datasets, improving training efficiency and outcomes.
  • 🤖 LLM Agent Systems
    Investigating the use of LLMs as intelligent agents in legal scenarios, addressing tasks such as legal document drafting, case retrieval, and statute matching to advance legal automation.

LLMs-as-Judges: Exploring the potential and applications of LLMs as intelligent evaluators. Key areas include:

  • 🎯 Performance Evaluation
    Researching how LLMs can assess model capabilities (e.g., generation quality, reasoning ability) and building unified evaluation frameworks.
  • 🚀 Model Evolution
    Utilizing LLM-based evaluation feedback to guide the design and optimization of new models, accelerating iterative development.
  • ⚖️ Bias Mitigation
    Developing more reliable LLM Judges to reduce biases and enhance fairness, ensuring trustworthy and equitable evaluation outcomes.

I am also deeply interested in LLMs for complex problem decomposition and solving, multi-agent collaboration, retrieval-augmented generation (RAG), and information retrieval. I look forward to collaborating and exchanging ideas with researchers in these exciting areas!


Education

  • 09.2022-present Master, Department of Computer Science and Technology, Tsinghua University, China.
  • 09.2018-06.2022 B.S., Electronic Engineering, Beijing University of Aeronautics and Astronautics, China.
  • 09.2019-06.2022 Minor, Mathematics, Beijing University of Aeronautics and Astronautics, China.

News

  • 12.2024 🎉 I was awarded the Shimo Zhong Scholarship, the highest honor in the Department of Computer Science at Tsinghua University, given to only six students each year.
  • 12.2024 📰 We released the first version of our survey on LLMs-as-Judges: [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods] [Github].
  • 06.2024 🌟 I am honored to have received the Siebel Scholars Award, a prestigious recognition given annually to only 83 scholars worldwide. Details here.
  • 05.2024 🥇 We participated in COLIEE 2024 - Legal Case Retrieval Task and won the first place! [Paper] [Code].
  • 04.2023 🏆 We participated in COLIEE 2023 - Legal Case Retrieval Task and won the first place! [Paper] [Code].
  • 04.2023 🎉 We participated in COLIEE 2023 - Legal Case Entailment Task and won the third place. [Paper] [Code].
  • 03.2023 🥈 We participated in WSDM Cup 2023 - Unbiased Learning & Pre-training for Web Search Task and won the second place!
  • 12.2022 🥈 I participated in CAIL2022 and won the second place. [Link].
  • 08.2022 🏅 We participated in LIC2022 and won the third prize. [Link].

Papers

  • BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models.
    Haitao Li, Qingyao Ai, Jia Chen, Qian Dong, Zhijing Wu, Yiqun Liu.
    (AAAI 2025)
    [Paper][Code]
  • DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment.
    Haitao Li, Qingyao Ai, Xinyan Han, Jia Chen, Qian Dong, Yiqun Liu.
    (AAAI 2025)
    [Paper][Code]
  • LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models.
    Haitao Li, You Chen, Qingyao Ai, Yueyue Wu, Ruizhe Zhang, Yiqun Liu.
    (NeurIPs 2024)
    [Paper][Code]
  • PRE: A Peer Review Based Large Language Model Evaluator.
    Zhumin Chu, Qingyao Ai, Yiteng Tu, Haitao Li, Yiqun Liu.
    (CIKM 2024)
    [Paper][Code]
  • Unsupervised large language model alignment for information retrieval via contrastive feedback.
    Qian Dong, Yiding Liu, Qingyao Ai, Zhijing Wu, Haitao Li, Yiqun Liu, Shuaiqiang Wang, Dawei Yin, Shaoping Ma.
    (SIGIR 2024)
    [Paper][Code]
  • LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset.
    Haitao Li, Yunqiu Shao, Yueyue Wu, Qingyao Ai, Yixiao Ma, Yiqun Liu.
    (SIGIR 2024)
    [Paper][Code]
  • I3Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval.
    Qian Dong, Yiding Liu, Qingyao Ai, Haitao Li, Shuaiqiang Wang, Yiqun Liu, Dawei Yin, Shaoping Ma.
    (CIKM 2023)
    [Paper]
  • An Intent Taxonomy of Legal Case Retrieval.
    Yunqiu Shao, Haitao Li, Yueyue Wu, Yiqun Liu, Qingyao Ai, Jiaxin Mao, Yixiao Ma, Shaoping Ma.
    (TOIS)
    [Paper]
  • THUIR@ COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrieval.
    Haitao Li, Weihang Su, Changyue Wang, Yueyue Wu, Qingyao Ai, Yiqun Liu.
    (COLIEE 2023)
    [Paper] [Code]
  • THUIR@ COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment.
    Haitao Li, Changyue Wang, Weihang Su, Yueyue Wu, Qingyao Ai, Yiqun Liu.
    (COLIEE 2023)
    [Paper] [Code]
  • Constructing Tree-based Index for Efficient and Effective Dense Retrieval.
    Haitao Li, Qingyao Ai, Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Zheng Liu, Zhao Cao.
    (SIGIR 2023)
    [Paper] [Code]
  • SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval.
    Haitao Li, Qingyao Ai, Jia Chen, Qian Dong, Yueyue Wu, Yiqun Liu, Chong Chen, Qi Tian.
    (SIGIR 2023)
    [Paper] [Code]
  • T^2Ranking: A large-scale Chinese Benchmark for Passage Ranking.
    Xiaohui Xie, Qian Dong, Bingning Wang, Feiyang Lv, Ting Yao, Weinan Gan, Zhijing Wu, Xiangsheng Li, Haitao Li, Yiqun Liu and Jin Ma.
    (SIGIR 2023)
    [Paper] [Code]
  • Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank.
    Haitao Li, Jia Chen, Weihang Su, Qingyao Ai, Yiqun Liu.
    (WSDM Cup 2023 Task2 (2/213 Teams))
    [Paper] [Code]
  • THUIR at WSDM Cup 2023 Task 1: Unbiased Learning to Rank.
    Jia Chen, Haitao Li, Weihang Su, Qingyao Ai, Yiqun Liu.
    (WSDM Cup 2023 Task1 (2/187 Teams))
    [Paper] [Code]
  • THUIR at the NTCIR-16 WWW-4 Task.
    Shenghao Yang, Haitao Li, Zhumin Chu, Jingtao Zhan, Yiqun Liu, Min Zhang and Shaoping Ma.
    (NTCIR 16)
  • Underexposed Image Enhancement via Unsupervised Feature Attention Network.
    Fengji Ma, Haitao Li.
    (ICME 2021)
  • A multi-level fusion network for airport capacity prediction.
    Wenbo Du, Shenwen Chen, Haitao Li, Zhishuai Li, Xianbin Cao, Yisheng Lv.
    (IEEE Transactions on Intelligent Transportation Systems (ITS))
  • A Visual Feedback Supported Intelligent Assistive Technique for ALS Patients.
    Zihao Wang, Aojie Zhang, Xinyue Xia, Sizhe Zhang, Haitao Li, Jiaqi Wang, Shuo Gao.
    (Advanced Intelligent Systems)

Honors and Awards

  • 2024 Shimo Zhong Scholarship 1/6, The highest honor in the Department of Computer Science at Tsinghua University.
  • 2024 Siebel Scholars Award 1/83 across the world, $30,000.
  • 2023 China National Scholarship.
  • 2022 Outstanding Contribution to the Beijing Winter Olympics and Paralympics, five volunteers in China.
  • 2022 Self-improvement Star of Chinese College Students.
  • 2022 Tianyi Scholarship.
  • 2022 Excellent Graduate of Beijing.
  • 2021 Special Award of Xiaomi Scholarship.
  • 2021 Feiyong Scholarship.
  • 2021 Segway-Ninebot Scholarship.
  • 2021 Huawei Intelligent Pedestal Scholarship.
  • 2021 Highest Undergraduate Honor Shen Yuan medal.
  • 2021 Row Model of Buaa.
  • 2021 The Challenge Cup: First Prize of Beijing.
  • 2021 China College Students Internet+ Innovation and Entrepreneurship Competition: Second Prize of Beijing.
  • 2021 IC Design Competition: First Prize, Second place in Beijing.
  • 2021 Excellent Student Leader of Beijing.
  • 2020 China National Scholarship.
  • 2020 Mathematical Contest in Modeling: Finalist Winner, top1% in the world.
  • 2020 China Undergraduate Mathematical Contest in Modeling: National Second Prize, First Prize of Beijing.
  • 2020 MathorCup: National Second Prize.

Experience

  • 09.2022-present Party branch secretary of jiyan 41, Tsinghua University.
  • 09.2022-present Class assistant, Tsinghua University.
  • 06.2022-09.2021 Minister of Volunteer Department, The School League Committee, Buaa.
  • 06.2020-09.2019 Chairman of College Student Union, Buaa.