Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
- George Kour
- Itay Nakash
- et al.
- 2025
- ACL 2025
I am a researcher in the Natural Language Processing group at IBM Research - Haifa. My work focuses on the safety and security of large language models, with particular emphasis on LLM-based agents, prompt injection attacks, and tool-augmented reasoning.
I hold a bachelor's degree in Computer Science and a master's degree in Data Science, both from the Technion - Israel Institute of Technology, completed under the supervision of Prof. Roi Reichart.