Yulong Chen

Yulong Chen is a Researcher at the Department of Computer Science and Technology, University of Cambridge. He specializes in Natural Language Processing (NLP), focusing on areas such as large language models (LLMs), constituency parsing, cross-lingual summarization, and dialogue systems. His work bridges theoretical advancements with practical applications, including automated claim verification, multimodal intelligence, and ethical AI considerations.

Chen contributes to both teaching and research: he teaches courses on Natural Language Processing at both undergraduate and postgraduate levels. His research emphasizes interdisciplinary approaches, combining machine learning, computational linguistics, and cognitive models. Key projects include developing benchmarks for higher-order theory of mind reasoning in LLMs and designing frameworks to uncover model weaknesses.

His publications span foundational surveys (e.g., on LLM hallucinations and text-to-SQL systems) to applied work like MACSum for controllable summarization and Hi-TOM for evaluating social cognition in AI. He collaborates extensively on tools like EASE for efficient data annotation and UniSumm for few-shot summarization, reflecting his commitment to advancing both NLP infrastructure and model capabilities.