Zhijing Jin

This article examines how language models balance factual and counterfactual information.

Combining causal relationships with prediction improves sentiment analysis accuracy.

An analysis of how Abstract Meaning Representation impacts LLM performance across various tasks.

New method improves documentation of AI models and datasets using advanced language models.

Examining fairness and ethics of how language models respond to users.

Analyzing how LLMs make moral choices across languages and cultures.

Examining accountability in human-AI collaborations across various fields.