Jiazheng Li
Scholar

Jiazheng Li

Google Scholar ID: EvRLcmMAAAAJ
King's College London
Natural Language ProcessingLarge Language ModelsExplainable AIAI for Education
Citations & Impact
All-time
Citations
504
 
H-index
12
 
i10-index
12
 
Publications
20
 
Co-authors
15
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Nov 2025: One main paper (multi-agent verbal reinforcement learning) and two demos on student answer assessment accepted at EMNLP 2025
  • Sep 2025: Work on mechanistic interpretability (residual stream activation-space auditing for CoT faithfulness) accepted at NeurIPS 2025 MechInterp Workshop
  • Jul 2025: Three papers accepted at ACL 2025 (Rationale Faithfulness, Neuron-Level Interpretation of Preference Optimisation, Theory-of-Mind Reasoning)
  • Jul 2025: Research featured by The Telegraph
  • Jul 2025: Position paper on Meta-Reasoning accepted at ICML 2025
  • Jun 2025: Selected for the second cohort of the KCL Spinout Accelerator; seeking investment
  • Jun 2025: Presented explainable student answer assessment system at FLIP+ conference, Netherlands
  • May 2025: Fact-checking paper accepted by IEEE TASLP
  • Feb 2025: Two papers on rationale generation for education and medicine accepted at AAAI 2025
  • Dec 2024: Paper on rationale alignment accepted for oral presentation at NeurIPS 2024 FM-EduAssess workshop
  • Nov 2024: Named outstanding reviewer at EMNLP 2024
  • Nov 2024: Three papers on preference optimisation and interpretability accepted at EMNLP 2024
  • Aug 2024: Dataset on complex narrative relation understanding accepted at ACL 2024
  • Mar 2024: Role-playing demo system accepted at EACL 2024
  • Mar 2024: Demo system accepted at AAAI 2024
  • Dec 2023: Workshop paper on batched zero-shot querying of LLMs accepted at NeurIPS 2023 R0-FoMo workshop
  • Dec 2023: Paper on explainable student answer assessment presented at EMNLP 2023
  • Multiple invited talks and panels at BERA 2023, ALTA (Cambridge), CGI, Imperial College London, etc.