Publications

(* Equal contribution, † Corresponding author)  |  Full list on Google Scholar

AI for Education

EMNLP 2025
LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
R. Zhao, A. Borov, J. Li, C. Aloisi, Y. He
EMNLP 2025
AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment
J. Li, A. Bobrov, R. Zhao, C. Aloisi, Y. He

AI for Health

BMJ Open 2026
Impacts of Epic MyChart and Healthy Planet on Clinical Care Measures: A Scoping Review Protocol
R. Plackett, A. Moro, R. Zhao, A. Ettefaghian, D. Lafitte, C. Reed, A. Hertelendy, T. Y. Wong, A. M. Sitapati, C. Longhurst, J. Car
Findings of ACL 2023
Disentangling Aspect and Stance via a Siamese Autoencoder for Aspect Clustering of Vaccination Opinions
L. Zhu, R. Zhao, G. Pergola, Y. He
EACL 2023
PANACEA: An Automated Misinformation Detection System on COVID-19 [code]
R. Zhao, M. Arana-Catania, L. Zhu, E. Kochkina, L. Gui, A. Zubiaga, R. Procter, M. Liakata, Y. He

Interactive Narrative & Games

ACL 2026
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding [code]
R. Zhao*, Q. Zhu*, H. Xu, B. Liang, L. Gui, Y. He
EMNLP 2025
Concise-SAE: Enhancing Instruction Adherence in LLMs via Sparse Latent Optimization under Narrative Disruption
R. Zhao*, C. Cao*, Q. Zhu, X. Lv, S. Shao, L. Gui, R. Xu, Y. He
Findings of ACL 2024
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives [code]
R. Zhao*, Q. Zhu*, H. Xu, J. Li, Y. Zhou, Y. He, L. Gui
AAAI 2024
NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing
R. Zhao*, W. Zhang*, J. Li*, L. Zhu, Y. Li, Y. He, L. Gui
Findings of EMNLP 2023
Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding
L. Zhu*, R. Zhao*, L. Gui, Y. He
Preprint
PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
Q. Zhu*, R. Zhao*, J. Du, L. Gui, Y. He

LLM Reasoning

ICML 2026
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
Z. Wu, G. Gong, Q. Zhu, Y. Chen, R. Zhao†
ICML 2025 Spotlight
Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
Q. Zhu*, R. Zhao*, H. Yan, Y. He, Y. Chen, L. Gui
ACL 2024
OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models
H. Xu, R. Zhao, L. Zhu, J. Du, Y. He
Tracking Brand-Associated Polarity-Bearing Topics in User Reviews [code]
R. Zhao, L. Gui, H. Yan, Y. He
TACL 2023
CONE: Unsupervised Contrastive Opinion Extraction [code]
R. Zhao, L. Gui, Y. He
SIGIR 2023
OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning
J. Li*, R. Zhao*, Y. Yang, Y. He, L. Gui
NeurIPS 2023 Workshop
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
Q. Zhu, Y. Yao, R. Zhao†, Y. Xiang, A. Saseendran, C. Jin, P. A. Teare, B. Liang, Y. He, L. Gui
Preprint