Sheikh Shafayat

About Me

Hi, I am an M.S. student at the KAIST School of Computing, advised by Alice Oh.

My current research interests include LLM reasoning (RLVR), AI creativity, and open-endedness. I closely collaborate with Andrea Zanette for projects related to LLM reasoning and self-improvement. I did my undergraduate at KAIST when I worked on evaluation, multilinguality, and cultural NLP.

A (partially) maintained CV of mine can be found here.

I am really open to meeting and chatting with new people. Feel free to send me an email if you want to chat about something (any paper, potential collaboration, a cool novel, or just about anything). If you are in Seoul and Daejeon, shoot me an email to grab a coffee or go climbing together! I will be an intern at MPI-SWS, Germany, working with Abhilasha Ravichander, starting January 5, 2026. If you happen to be in Europe, let’s try to meet in person!

On my free time, I enjoy bouldering, running, or basking in the sunset with a novel.

Research Interests

• NLP: LLM reasoning, algorithmic creativity, open endedness, multilinguality

News

• [May. 2025] New Preprint: Can Large Reasoning Models Self-Train?
• [Dec. 2024] New Preprint: A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls
• [July. 2024] MultiFAct for Multilingual Factuality got accepted to COLM-2024
• [May. 2024] BEnQA got accepted to ACL Findings
• [Apr. 2024] MultiFAct got accepted to ICLR Global AI Cultures Workshop

Publications

Current Readings

Here are a few latest books that I am reading/just finished. I am happy to receive book recommendations from anyone!

• East of Eden (John Steinbeck): This is the most American book I have ever read. A fantastic two family saga relating war, violence, love, immigration, assimilation, capitalism, westward expansion, corruption and moral ambivalence. This book does a justice to the first generation of Chinese American experience. The characterization of Lee, a Chinese American, as one of the central moral pillars of the story was way ahead of its time (1952).
• Nexus (Yuval Noah Harari): Very interesting read on the role of information technology in sustaining large scale human networks. My position on this book is somewhat mixed. While I find Harari’s thesis on how information networks and intersubjective reality shape human history to be absolutely brilliant, he seems to be deeply mistaken on the current state of AI progress and what it means by intelligent, decison making systems. I love the part I of the book, but part II? Not so much.
• Kafka on the Shore (Haruki Murakami): This is my second Murakami book after Norwegian Wood. The writing style and some recurring themes are strikingly similar. Kafka on the Shore was a dreamy, melancholic, and soothing read that made me think about the role of memory, strength and human fragility. It is the memories we live by, live for and hold onto.
• Flowers for Algernon (Daniel Keyes): This is such a tiny novella, yet so powerful. An intellectually disabled person goes through surgical procedure to 3 fold his IQ. The book is a daily reflection journal of the man. As a result of the surgery, he slowly becomes smarter in every page. But as he becomes smarter, he becomes more self-concious, less happy and less kind. As someone working in artificial intelligence, this novella made me think for a long time.

Powered by Jekyll and Minimal Light theme.