PhD Student in Computer Science,
Beijing Institute of Technology
I used to study Cross-lingual Summarization to investigate how to better generate text with low-resource data. As large language models (LLMs) continue to gain popularity, I am curious about why they are competent in so many challenging tasks. Hence, I have begun to think of LLMs as natural objects. By studying their working mechanisms and characteristics, I aim to understand these models more deeply and use these insights to improve them in terms of their generation quality, controllability, and safety.