🚀 Updates: As an incoming assistant professor at King’s College London (fall 2025), I am actively recruiting passionate PhDs and Master’s students interested in interpretable and robust reasoning with language models.

Hi everyone! I’m a PostDoc (01.2024-) at King’s College London, NLP Group, School of Informatics. I passed my PhD viva with no corrections after a great time at the University of Warwick (10.2020-01.2024), advised by Prof. Yulan He and Dr. Lin Gui. I finished my M.S. at Peking University(09.2017-07.2020) and my B.E. at Beihang University(09.2013-06.2017).

During Ph.D., I started my Causality Journey(10.2022-02.2023) in visiting Prof. Kun Zhang affiliated with the Causal Learning and Reasoning Group@CMU. Before Ph.D., I started my NLP journey(07.2019-10.2019) in visiting Prof. Wenjie Li affiliated NLP Group @PolyU Hong Kong.

I’ve been incredibly lucky to have a number of amazing collaborators and mentors across KCL and a range of other institutions, including Carnegie Mellon University, MIT, Peking University, MBZUAI, Hong Kong Polytechnic University, University College London,University of Warwick. None of the research so far—would be possible without their kind help and support.

🔍 Research Summary

My research interests lie in the intersection of Machine Learning and Natural Language Processing, i.e., incorporating fundamental representation learning to enhance the interpretability and reliability of different NLP models, with 10+ (co-)first-authored papers published at top-tier venues:

• Mechanistic interpretability (neuron-level) in language models and multi-modal models [EMNLP24,NeurIPS24-RBMF]; self-explainable models with a conceptualised layer linking the input and decision layer [Computational Linguistics 22,TKDE24].
• Empirical and principled methods to enhance model robustness over various test inputs, e.g., position bias [ACL24-findings,ACL21-oral], distribution shifts [NeurIPS23] and representation inefficiency in transformer-based models [EMNLP24,EACL23-findings,UAI22-spotlight].
• Understanding and enhancing LM’s reasoning capabilities via injecting external knowledge[ACL21-oral][ACL25], weak supervision [EMNLP24], applying a self-refinement mechanism for factual knowledge reasoning [ACL24]. More recently focus in the two directions:
  • Science literature understanding, such as code generation for scientific paper replication on our own SciReplicate-Bench and novelty assessment.
  • Reasoning in latent space, such as a position paper at ICML25 about meta-reasoning, CODI in implicit CoT, in retrieved-based QA [ACL25], navigating search in latent space [ICML25spotlight] and sparse feature for preference optimization [ICML25].

🔥 News

👩‍🏫 Professional Service

• Co-Chair of the Asian Chapter of the Association for Computational Linguistics (Student Research Workshop) 2022
• Organiser of Event - PreTrain 2025: Spotlight on ACL/ICML/ICLR at King’s College London
• Area Chair: ACL25, EMNLP25
• Reviewers:
  • NLP: AACL, NAACL, EACL, EMNLP, ACL, COLM25
  • AI/ML: UAI, AISTATS, NEURIPS, ICLR, ICML, AAAI26
  • Journal: NeuroComputing, TOIS, TMLR, Transactions on Big Data, Transactions on Artificial Intelligence.

💬 Invited Talks

• University of Southampton, Computer Science , 04/2025. LLM Reasoning with internal and controllable signals
• University of Surrey, Computer Science , 04/2025. Controllable generation framework for LLM reasoning
• University of Bath, Computer Science , 04/2025. Disentanglement for interpretability and controllability
• University of Birmingham, Computer Science , 12/2024. Understanding and improving LLM reasoning via representation learning
• Huawei, LLM research team in Singapore (Remote) . Controllable generation and Causality in LLMs.
• Amazon, Artificial Generative Intelligence team in London (Remote) . Robust and Interpretable NLP via Representation Learning and Applications in LLMs.
• Fudan University, NLP Group , 07/2024. Representation Learning and Mechanistic Interpretability
• UC San Diego, NLP Group , 02/2024. Robust and Interpretable NLP via representation learning and Path Ahead
• Yale University, NLP Group 01/2024. Robust and Interpretable NLP via representation learning and Path Ahead
• Turing AI Fellowship Event , London, 03/2023, Distinguishability Calibration to In-Context Learning
• UKRI Fellows Workshop , University of Edinburgh, 04/2022. Interpreting Long Documents and Recommendation Systems via Latent Variable Models

📝 Publications

(* indicates equal contribution)

📝 Notes

o1-technical report (notes for video)
Machine Unlearning via CausalLens and in NLP tasks
Reading List For Large Language Model
Identifiability101 in Causality (3rd PhD)
Induction Head_ contribute to In-context Learning (3rd PhD)
Recommendation with Causality (2nd PhD)
Causality101 (Feb 2022, 2nd PhD)
Explaining Neural Networks (Oct 2020 1st PhD)