Jiazheng Li I'm a PhD candidate focusing on Natural Language Processing at the King's College London's NLP group, under the supervision of Prof. Yulan He. My PhD is funded by the AQA Education, where I work on Explainable Automated Student Answer Scoring Systems built on Large Language Models. Before my PhD, I obtained a First-Class honours bachelor’s degree in computer science from the University College Dublin in 2021.

Research

For my academic publications and patents please refer to my Google Scholar profile.

Research Interests:

• Machine Learning

• Natural Language Processing

  • Large Language Models

    • Explainability: Rationale Generation, Uncertainty, Mechanistic Interpretability;

    • Alignment: Preference Optimisation, Inference-time Reinforcement Learning;

    • Applications: Agents, Multimodal LLM, Role Playing, Educational Assessment.

Here are my GitHub and Huggingface profiles. You can also connect me on LinkedIn and Twitter.

I'm actively looking for research internships. CV can be provided upon request.

News

Feb 2025: Two papers related to rationale generation accepted at AAAI 2025.
Jan 2025: My research has been featured in the KCL News.
Dec 2024: One paper on assessment rationale alignment accepted for oral presentation at NeurIPS 2024 FM-EduAssess.
Nov 2024: Named as one of the outstanding reviewers at EMNLP 2024.
Nov 2024: Three papers centered on preference optimisation and interpretability accepted at EMNLP 2024. (Explainable Student Assessment, Preference Optimisation, ICL Interpretability)
Aug 2024: One dataset on complex narrative relation understanding accepted to ACL 2024.
Jun 2024: Gave a talk at the TLDR Group, Imperial College London.
May 2024: Delivered a seminar on interpretable text classification at CGI.
Mar 2024: One paper on role-playing demo system accepted at EACL 2024.
Mar 2024: Gave a talk on explainable student answer assessment at the ALTA group, University of Cambridge.
Mar 2024: One demo system accepted at AAAI 2024.
Dec 2023: One workshop paper on batched zero-shot query LLMs accepted at NeurIPS 2023 R0-FoMo.
Dec 2023: One paper on explainable student answer assessment presented at EMNLP 2023.
Dec 2023: Gave a talk at MMLM.
Sep 2023: Gave a presentation and panel talk at BERA 2023 on AI assessment.
Aug 2023: One paper on uncertainty interpretation accepted as spotlight presentation at UAI 2023.
May 2023: Presented two posters at the UKAI Fellows Conference.