Hi there 👋

I am Yulin Chen, a PhD student at New York University, co-advised by Prof. Chen Zhao and Prof. He He. I am generally interested in understanding language model behaviors, particularly on reasoning and representation engineering/alignment. I obtained bachelor and master degrees both from Tsinghua University. During my master, I have worked on prompting and large language model alignment at THUNLP.

📢 News

• [2026.05] 🎉 One paper accepted to ICML 2026 on unlearnability phenomenon in RLVR
• [2025.09] One paper accepted to COLM 2025 on understanding reasoning models

🎓 Education

• Ph.D. in Data Science, New York University, 2024-present
• M.S. in Computer Science, Tsinghua University, 2021-2024
• B.A. in Linguistics, Tsinghua University, 2017-2021

📄 Selected Publications

• Zhang A, Chen Y, Pan J, et al. Reasoning Models Know When They’re Right: Probing Hidden States for Self-Verification. COLM 2025. [Paper] [Code]
• Chen Y, Ding N, Zheng H, et al. Empowering Private Tutoring by Chaining Large Language Models. CIKM 2024. [Paper]
• Ding N*, Chen Y*, Xu B, et al. Enhancing Chat Language Models by Scaling High-quality Instructional Conversations. EMNLP 2023. [Paper]
• Chen Y, Ding N, Wang X, et al. Exploring Lottery Prompts for Pre-trained Language Models. ACL 2023. [Paper]
• Wang X*, Chen Y*, Ding N, et al. MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction. EMNLP 2022. [Paper]
• Ding N*, Xu G*, Chen Y*, et al. Few-NERD: A Few-shot Named Entity Recognition Dataset. ACL 2021. [Paper]

💼 Working Experience

• Teaching Assistant for DSGA 1011 Fundamentals of Natural Language Processing, Fall 2025