👋 About

I am Xin Chen, a first-year joint Ph.D. student in Computer Science at Nanjing University, under the supervision of Prof. Min YANG and Prof. Shujian HUANG.

My research interests encompass Privacy-preserving and Trustworthy AI, the application of Large Language Models (LLMs) to real-world scenarios such as healthcare and finance, and the detection of AI-generated content (AIGC).

🌟 Research Interest

• Trustworthy AI
• 🔳 AIGC Detection with Junchao WU
• ⬜️ Privacy-preserving AI
• Dialogue System
• 🔳 Proactive Interactive System with Feng JIANG
• ⬜️ LLMs to Real-world Scenarios(e.g., healthcare, finance)

❗️ News

• [2026-01-30] Our new preprint Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers released. We propose a Proactive Interactive Reasoning framework that enables reasoning-LLMs to proactively ask clarification questions to resolve user ambiguity, significantly improving accuracy and efficiency.
• [2026-01-26] Our work accepted by ICLR 2026: Neuron-Aware Data Selection in Instruction Tuning for Large Language Models. We propose the Nait framework, which selects optimal instruction tuning data samples by analyzing the similarity of neuron activation patterns.
• [2025-09-01] Our Work RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns has been notified that will be presented at The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). Looking forward to an insightful discussion at the conference! See you in Suzhou, China!
• [2025-08-01] One Paper accepted by Transactions of the Association for Computational Linguistics (TACL) as first author: RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns. We propose RepreGuard, a low-overhead, highly generalizable, and interpretable detector, based on the observation that there are significant differences in neural activation patterns when LLMs process LLM-generated text versus human-written text.
• [2025-04-03] Our new preprint Understanding Aha Moments: from External Observations to Internal Mechanisms released. We reveal that “aha moments” help LRMs solve complex problems by using anthropomorphic language, adjusting uncertainty, and preventing reasoning collapse, while internally balancing self-reflection with reasoning and adapting to task difficulty.
• [2024-06-15] Our paper related with the Explainable artificial intelligence (XAI): A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning. 📫 More ====== If you have any questions or cooperation, please feel free to contact me by Email: x.chen@smail.nju.edu.cn