✨ Hi everyone! I’m a PostDoc (01.2024-) at King’s college London, NLP Group,led by Prof. Yulan He. I passed my PhD viva with no corrections after a great time in University of Warwick (10.2020-04.2024), 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 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.
🔍 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.
- 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 [CL22,TKDE24].
- Empirical and principled methods to enhance model robustness over various test inputs, e.g., position bias [ACL24-findings,ACL21], distribution shifts [NeurIPS23] and inherited representation inefficiency in transformer-based models [EMNLP24,EACL-findings,UAI22].
- Understanding and enhancing LLM’s reasoning capabilities via inject weak supervision [EMNLP24] and apply self-refinement framework [ACL24].
🔥 News
10.2024: 🔥 A first-author paper about monosemantic neuron in multi-modal model is accepted by Neurips-RBMF workshop.
09.2024: Three papers (monomsemantic neurons, oral survey in ICL, weak2strong event extraction) are accepted by EMNLP24 Main Conference. 🎉
08.2024: I go to Bangkok, Thailand🇹🇭 for ACL24. ✈️
05.2024: Two papers (1 first-author) are accepted by ACL24, one in the main conference, one in findings.
04.2024: I pass the PhD viva with no correction🎓.
01.2024: I become a PostDoc👩🏫 at King's College London, NLP Group.
01.2024: I finish my PhD thesis (draft) on the same day of my birthday.
01.2024: My first-author paper is finally accepted by TKDE.
12.2023: I go to New Orleans🎷, US to present our Neurips paper.
07.2023: I go to Hawaii🌴, US to present our ICML-workshop paper.
07.2023: My first-author paper is accepted by Neurips (my Neurips paper).
02.2023: I go back to the UK from Abu Dhabi, UAE🇦🇪, finish my Machine Learning trip in MBZUAI.
02.2023: I attend the EMNLP23 held in Abu Dhabi, to present our Computational Linguistics paper.
01.2023: One paper is accepted by EACL23🇭🇷-findings (first time as a mentor for a master's student).
12.2022: Lionel Messi leads Argentina to win the ⚽️World Cup championship.
10.2022: I start to be a funded visiting student in Machine Learning, Department at MBZUAI🏫, Abu Dhabi, UAE, advised by Prof. Kun Zhang.
08.2022: I go to Eindhoven, Netherlands🇳🇱 to present our UAI paper.
05.2022: My first-author paper is accepted by UAI23 (🥳my first ML paper)
05.2021: The first time! My first-author paper is accepted by ACL21 🌟Oral A super encouragement in my early PhD career.
10.2020: I start my PhD📚 journey at University of Warwick, UK🇬🇧.
🚀 I am always open to new collaborations and engaging discussions. Feel free to reach out if you are interested in working together or just want to chat!
📝 Selected Publications
(* indicates equal contribution)
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
H. Yan, Y. Xiang, G Chen, Y. Wang, L. Gui, Y. He
EMNLP24, main | Paper
Interpretability Representation
Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems
I. Silva, H. Yan, L. Gui, Y. He
EMNLP24, main | Paper
Causality application
The Mystery and Fascination of LLMs: A Comprehensive Survey on the Interpretation and Analysis of Emergent Abilities
Y. Zhou, J. Li, Y.Xiang, H.Yan, L. Gui, Y. He
EMNLP24, main | Paper
Interpretability
Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
H. Yan, Q. Zhu, X. Wang, L. Gui, Y. He
ACL24, main | Paper
application
Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models.
Y. Xiang, H. Yan, L. Gui, Y. He
ACL24, findings | Paper
Representation
Counterfactual Generation with Identifiability Guarantee
H. Yan, L. Kong, L. Gui, Y. Chi, Eric. Xing, Y. He, K. Zhang
Neurips23, main | Paper
Causality Representation application
Explainable Recommender with Geometric Information Bottleneck
H. Yan, L. Gui, M. Wang, K. Zhang and Y. He
TKDE | Paper
Interpretability application
Hierarchical Interpretation of Neural Text Classification
H. Yan, L. Gui and Y. He
Computational Linguistics, Present at EMNLP23 | Paper
Interpretability application
Addressing Token Uniformity in Transformers via Singular Value Transformation
H. Yan, L. Gui, W. Li and Y. He
UAI22, spotlight | Paper
Representation
Distinguishability Calibration to In-Context Learning
H. Li, H. Yan, L. Gui, W. Li and Y. He
EACL23, findings | Paper
Representation
A Knowledge-Aware Graph Model for Emotion Cause Extraction
H. Yan, L. Gui and Y. He
ACL21, Oral | Paper
Causality application
👩🏫 Professional Actitives
- Event Organiser: Co-Chair of AACL-IJCNLP (Student Research Workshop) 2022
- Reviewers:
- AACL23’24
- NAACL24’
- EACL23’
- EMNLP22’23’24’
- ACL23’24’
- UAI23’
- AISTATS24’25’
- NEURIPS24’
- ICLR25’
- NeuroComputing
- TOIS
💬 Invited Talks
- 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