Hi! I’m Chenxi Wang (Aurora), a second-year M.Sc. student in NLP at MBZUAI, supervised by Prof. Xiuying Chen. Prior to MBZUAI, I got my B.Eng. degree in Computer Science at Xi’an Jiaotong University.
My research focuses on human-centric AI. Integrating insights from cognitive science, psychology, and philosophy, I use interpretability methods to uncover the cognitive and reasoning mechanisms within large language models (LLMs). I believe that the knowledge and behaviors exhibited during default inference represent only a fraction of what these models truly contain. To unlock these hidden potentials, I take an interpretability-first post-training approach that awakens latent capabilities which do not spontaneously emerge, enabling models to adaptively express specific skills or reasoning patterns during inference without additional large-scale pretraining. Ultimately, my goal is to pave the way for personalized and human-aligned AI, building a virtuous cycle where human intelligence inspires AI, AI evolves through this understanding, and the progress of AI, in turn, better serves human well-being.
🌟 My current work explores interpretable post-training methods that make LLMs more adaptable, transparent, and cognitively grounded, enabling them to reason, communicate, and align more effectively with diverse human goals.
I welcome thoughtful discussions on dependency risk, and I’m happy to chat about philosophy of mind and what makes AI feel more human :)
Actively seeking PhD positions for Fall 2026. Please see my CV and feel free to get in touch.
🔥 News
- Oct 2025: ✨My first-author paper “Do LLMs ‘Feel’? Emotion Circuits Discovery and Control” was featured by the academic X (Twitter) account AIDB, reaching 194k+ views, 1.3k+ likes, 650+ bookmarks, and 450+ shares in five days 🥳. [Post Link]
- Oct 2025: One paper accepted to AAAI 2026.
- Aug 2025: One first-author paper accepted to EMNLP 2025.
- Aug 2025: 🎤 Poster presentation at ACL 2025 (Vienna).
- Jun–Aug 2025: Research internship at Peking University (Beijing)🇨🇳.
- May 2025: One first-author paper accepted to ACL 2025.
- Jan 2025: 🎤 Poster presentation at COLING 2025 (Abu Dhabi).
- Nov 2024: One first-author paper accepted to COLING 2025.
- Sep 2024: 🎉 My very first research paper accepted to NeurIPS 2024.
- Aug 2024: 🎓 Started my M.Sc. in NLP at MBZUAI.
📝 Publications
🌟 First-/Co-first-author publications
I value making my work reproducible and open (very much) 🤗.
Do LLMs “Feel”? Emotion Circuits Discovery and Control
Chenxi Wang, Yixuan Zhang, Ruiji Yu, Yufei Zheng, Lang Gao, Zirui Song, Zixiang Xu, Gus Xia, Huishuai Zhang, Dongyan Zhao, Xiuying Chen†
[Code]
Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
Chenxi Wang, Yixuan Zhang, Lang Gao, Zixiang Xu, Zirui Song, Yanbo Wang, Xiuying Chen†
[Code]
Word Form Matters: LLMs’ Semantic Reconstruction under Typoglycemia
Chenxi Wang, Tianle Gu, Zhongyu Wei, Lang Gao, Zirui Song, Xiuying Chen†
[Code]
Decoding echo chambers: Llm-powered simulations revealing polarization in social networksPreprint
Chenxi Wang*, Zongfang Liu*, Dequan Yang, Xiuying Chen†
[Code]
Autonomous Agents for Collaborative Task under Information Asymmetryt
Wei Liu*, Chenxi Wang*, Yifei Wang, Zihao Xie, Rennai Qiu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Chen Qian†
[Code]
🌈 Recent Co-authored publications
Zirui Song, Guangxian Ouyang, Mingzhe Li, Yuheng Ji, Chenxi Wang, Zixiang Xu, Zeyu Zhang, Xiaoqing Zhang, Qian Jiang, Zhenhao Chen, Zhongzhi Li, Rui Yan, Xiuying Chen†
DyFlow: Dynamic Workflow Framework for Agentic Reasoning
Yanbo Wang, Zixiang Xu, Yue Huang, Xiangqi Wang, Zirui Song, Lang Gao, Chenxi Wang, Xiangru Tang, Yue Zhao, Arman Cohan, Xiangliang Zhang, Xiuying Chen†
Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World
Saeed Almheiri, Rania Hossam, Mena Attia, Chenxi Wang, Preslav Nakov, Timothy Baldwin, Fajri Koto†
Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen†
Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
Lang Gao, Kaiyang Wan, Wei Liu, Chenxi Wang, Zirui Song, Zixiang Xu, Yanbo Wang, Veselin Stoyanov, Xiuying Chen†
Experience
Education
- [08 / 2024 - 06 / 2026]
M.Sc. in Natural Language Processing, MBZUAI, UAE - [09 / 2019 - 06 / 2023]
B.Eng. in Computer Science, Xi’an Jiaotong University, China
Internship Experience
- [06 / 2025 - 08 / 2025]
Research Intern, State Key Laboratory of General Artificial Intelligence, Peking University (Supervisor: Prof. Dongyan Zhao) - [03 / 2024 - 09 / 2024]
Research Intern, THUNLP Lab, Tsinghua University (Mentor: Wei Liu) - [07 / 2023 - 03 / 2024]
NLP Intern, Trust & Safety ML Team, Xiaohongshu (RedNote)
🫶🏻 I am deeply grateful to all the mentors and collaborators who have guided and supported me along the way. I’ve learned a great deal from each of them.
🫡 Service
Reviewer: ICLR 2025, EMNLP 2025.
👾 Miscellaneous
Outside research, I enjoy philosophy, history documentaries, and the writings of Borges. I like the calm and timeless way they invite me to think. After long nights in the lab, I often walk to Masdar Park near campus to watch the stars and think about those timeless questions: who we are, where we come from, and where we are going.
I also love traveling. I enjoy exploring cultural landscapes and getting a glimpse of everyday life, sitting in cafés where locals gather and imagining the world through their eyes. Sometimes it’s a Dutch herring sandwich by the canals in Amsterdam; sometimes it’s a Nutella kunafa in Abu Dhabi (my favorite, though my Arab friends insist it’s a crime against tradition).
These experiences have shaped my taste in research — I hope to do work that holds real value for humanity itself.
Last updated: October 2025