avatar

Caiqi Zhang

Ph.D. Student
University of Cambridge
c_iq_.zh_ng@outlook.com
(substitute '_' with human intelligence)


🙋 About Me

I am a third year Ph.D. student at the University of Cambridge, working under the supervision of Prof. Nigel Collier. Previously, I completed my MPhil degree at Cambridge, focusing on fact-checking under the guidance of Prof. Andreas Vlachos and Dr. Zhijiang Guo.

During my PhD studies, I did research internships in Microsoft Research, J.P. Morgan AI Research, and Tencent AI Lab.

During my undergraduate studies, I interned at PlusLab (UCLA) working with Dr. Nanyun Peng and Dr. Te-Lin Wu, and completed my capstone project with Prof. Wenjie Li and Dr. Yongqi Li at PolyU NLP Group.

📚 Education

Undergraduate Scholarships:
  • • HKSAR Government Scholarship 2020/21 and 2021/22 (HKD 160,000, around USD 20,500)
  • • Commercial Radio 50th Anniversary Scholarship 2019/20 (HKD 80,000, around USD 10,250)
  • • The Hong Kong Polytechnic University Scholarship 2019/20 (HKD 40,000, around USD 5,125)
  • • Wong Tit-shing Student Exchange Scholarship 2020/21 (HKD 20,000, around USD 2,560)
  • • WKF Foundation Service-Learning Scholarship 2020/21 (HKD 16,600, around USD 2,125)
  • • Wei Lun Foundation Scholarship 2020/21 (HKD 16,600, around USD 2,125)
  • • Tellhow Group Scholarship 2018/19 (CNY 10,000, around USD 1,399)
  • • Rennie's Mill Student Aid Project Alumni Association Scholarship 2019/20 (HKD 10,000, around USD 1,250)
  • • V.K. Hsu & Sons Foundations Ltd. Scholarship 2019/20 (HKD 10,000, around USD 1,250)
  • • HKMA IT Management Club Scholarship 2021/22 (HKD 5,000, around USD 640)
  • • Proof-of-Concept (POC) Funding Scheme 2021/22 (HKD 5,000, around USD 640)

👨‍💻 Internships

🗺️ Research Roadmap

💡My Research Vision: Our need for uncertainty in LLMs depends on how we position them.

My research studies these three connected dimensions of uncertainty in LLMs: measurement, expression, and interaction.

graph LR %% --- NODES & HIERARCHY --- %% Root Node Root(("🌲 Uncertainty
in LLMs")) %% --- Branch 1: Measurement --- Root --> Measurement("📐 Measurement") Measurement --> M_Fact["Long-form Factuality"] M_Fact --> LUQ["📄 LUQ: First work on long-form UQ
(EMNLP '24)"] M_Fact --> Atomic["⭐ Atomic Calibration
(IJCNLP '25)"] Measurement --> M_Reason["Reasoning"] M_Reason --> Rome["🗺️ All Roads Lead to Rome
(EMNLP '25)"] Measurement --> M_Multi["Multilingual"] M_Multi --> Beyond["🏗️ Beyond Final Layer
(Preprint)"] %% --- Branch 2: Expression --- Root --> Expression("🗣️ Expression") Expression --> E_Bench["Benchmarking"] E_Bench --> UNCLE["📏 UNCLE: Benchmarking
(EMNLP '25)"] Expression --> E_Learn["Learning to Express"] E_Learn --> LoGU["💬 LoGU: Linguistic Expressions
(ACL '25)"] E_Learn --> RL["🧠 RL for Verbalized Confidence
(Preprint)"] %% --- Branch 3: Interaction --- Root --> Interaction("🤝 Interaction") Interaction --> I_Social["Social Influence"] I_Social --> Conformity["👥 Uncertainty leads to conformity
(ACL '25)"] Interaction --> I_Multi["Multi-turn & Debate"] I_Multi --> ConfMulti["🔄 Confidence in Multi-turn
(Preprint)"] I_Multi --> MAD["🎙️ Confidence & Diversity in Debate
(Preprint)"] %% --- LINKS --- click LUQ "https://aclanthology.org/2024.emnlp-main.299/" "View Paper" click Atomic "https://arxiv.org/abs/2410.13246" "View Paper" click LoGU "https://arxiv.org/abs/2410.14309" "View Paper" click UNCLE "https://arxiv.org/abs/2505.16922" "View Paper" click RL "https://arxiv.org/abs/2505.23912" "View Paper" click Beyond "https://www.arxiv.org/abs/2510.03136" "View Paper" click Rome "https://arxiv.org/abs/2509.12908" "View Paper" click Conformity "https://arxiv.org/abs/2410.12428" "View Paper" click ConfMulti "https://arxiv.org/abs/2601.02179" "View Paper" click MAD "https://arxiv.org/abs/2601.19921" "View Paper" %% --- STYLING --- classDef main fill:#ffffff,stroke:#03396c,stroke-width:2px,color:white,font-size:14px; classDef domain fill:#ffffff,stroke:#03396c,stroke-width:2px,rx:10,ry:10,color:#03396c,font-size:13px; classDef label fill:#fff,stroke:none,color:#666,font-size:12px; classDef paper fill:#fff,stroke:#ddd,stroke-width:1px,rx:5,ry:5,color:#333,font-size:12px; %% Apply Classes class Root main; class Measurement,Expression,Interaction domain; class M_Fact,M_Reason,M_Multi,E_Bench,E_Learn,I_Social,I_Multi label; class LUQ,LoGU,UNCLE,RL,Rome,Beyond,ConfMulti,Atomic,Conformity,MAD paper;

📝 Publications

Core Research: Uncertainty in LLMs († denotes equal contribution.)

Other First & Co-First Papers

Other Collaborations (Full List: Google Scholar)

👀 More facts about me:

Volunteer Teaching

During term breaks, I volunteered in various teaching trips to rural areas globally, covering Hong Kong, Taiwan, Guilin, Ho Chi Minh City (Vietnam), Phnom Penh (Cambodia), and Trà Vinh (Cambodia). I've participated in 10+ voluntary services, accumulating 400+ service hours, benefiting 300+ students. Also, I joined the United Nations' Millennium Fellowship 2021 to promote equal education.

Mandarin Debate

As a member of both the PolyU and Cambridge Mandarin Debate Teams, I participated in competitions across various cities, including Singapore, Shanghai, Suzhou, Nanjing, Wuhan, Changsha, Xi'an, and Chengdu. These experiences refined my communication and critical thinking skills and provided international representation opportunities.


Less is more. -Ludwig Mies Van der Rohe

Flag Counter