Research Interests (Publications)

I enjoy exploring/building things that are novel and impactful (in research and life). My current research focuses on developing intelligent agents that can acquire, discover, and self-improve from new knowledge, while being trustworthy, explainable, and aligned with human values.

• Document Understanding and Knowledge Acquisition in the Dynamic World: How do we create efficient and logically sound NLP systems capable of extracting structured factual knowledge from lengthy and intricate documents. How do we represent contextual information such as "memory" and "time"? How do we build efficient systems that can detect incoherent predictions, as well as improve their consistency?


• Trustworthy Knowledge and Reasoning Capability: How do we enable NLP systems / LLM to conduct faithful and explainable reasoning across modalities. Specifically, How do we leverage contextual and external knowledge into end-to-end models, reasoning for better faithful and factual behaviors? How can we exploit models to induce new rules and hypotheses; and understand the reasoning capabilities of large pre-trained models? How do we comprehensively evaluate their reasoning capabilities and the transparency of explanations, which align closely with human judgements?


• NLP and Science (where "Science" includes General, Chemistry, Biomedical, etc.) / Computer Vision / Human–computer interaction : How do we LLM-based frameworks for generating scientific hypothesese, implementing and executing scientific experiments in an autonomous way. How do we design NLP techniques across modalities and for interdisciplinary research. How do we better align LLMs with human values? How do we enable models (or humans) to understand community policies and behave accordingly?