I’m a first year PhD student from Fudan University. My research interest includes natural language processing, LLM, and social computing.

I am very fortunate to be advised by Prof. Zhongyu Wei from School of Data Science, Fudan University.

Email / Github

📝 Publications

• FIRE: Flexible integration of data quality ratings for effective pre-training, Xu Liangyu, Xuemiao Zhang, Feiyu Duan, et al. EMNLP 2025

• FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy, Xuemiao Zhang, Feiyu Duan, Xu Liangyu, et al. Findings of ACL 2025

• Preference curriculum: Llms should always be pretrained on their preferred data, Xuemiao Zhang, Xu Liangyu, Feiyu Duan, et al. Findings of ACL 2025

• Enhancing llms via high-knowledge data selection, Feiyu Duan, Xuemiao Zhang, Sirui Wang, et al. AAAI 2025

• LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation, Keheng Wang, Feiyu Duan, Peiguang Li, et al. COLING 2025

• PositionID: LLMs can control lengths, copy and paste with explicit positional awareness, Noah Wang, Feiyu Duan, Yibo Zhang, et al. Findings of EMNLP 2024

• Generative Spoken Language Modeling with Quantized Feature Enhancement, Feiyu Duan; Chen Li; Keheng Wang, et al. IJCNN 2024

📄 Preprint

• Hellobench: Evaluating long text generation capabilities of large language models, Haoran Que, Feiyu Duan, Liqun He, et al. Arxiv

• Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering, Keheng Wang, Feiyu Duan, Sirui Wang, et al. Arxiv

📖 Educations

• 2025.09 - now, DISC Lab, Fudan NLP, Fudan University.
• 2022.09 - 2025.06, Sino-French Engineering School, Beihang University.
• 2018.09 - 2022.06, Sino-French Engineering School, Beihang University.

💻 Internships

• 2023.06 - 2024.08, LLM Algorithm Engineer, Meituan, Beijing, China.