I am a third-year NLP Ph.D. student at the University of Cambridge, Language Technology Lab (LTL). I am supervised by Professor Nigel Collier and advised by Dr. Ivan Vulic. My current research focuses on developing Personalized LLM Assistants through studying personalized alignment, collaborative agents, and online user feedback.

(1) Personalized Alignment: Aligning models with diverse global users through personalized preference learning, reward modeling, and subjective reasoning.
(2) Collaborative Agents: Training models to better interact and collaborate with humans, including agents that ask clarification questions at appropriate times and collaborate with users with different backgrounds.
(3) Self-evolution: Leveraging naturally occurring explicit and implicit feedback (critiques, preferences, edits) to continually adapt models to specific users and tasks at deployment.

Previously, I earned my undergraduate and master’s degrees from the University of Pennsylvania, where I was advised by Professor Chris Callison-Burch. I have also interned at Amazon, Roblox, and Sequoia Capital.

Publications

When Personalization Meets Reality: A Multi-Facet
Yijiang River Dong, Tiancheng Hu, Yinhong Liu, Ahmet Üstün, Nigel Collier
In Findings of Empirical Methods in Natural Language Processing (EMNLP 2025)

Can LLM be a Personalized Judge?
Yijiang River Dong, Tiancheng Hu, Nigel Collier
In Findings of Empirical Methods in Natural Language Processing (EMNLP 2024)

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramon Huerta, Ivan Vulić
In Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL 2025)

CORRPUS: Codex-Leveraged Structured Representations for Neurosymbolic Story Understanding
Yijiang River Dong, Lara J Martin, Chris Callison-Burch
In Findings of the Association for Computational Linguistics (ACL 2023)