An Analysis of Hyper-Parameter Optimization Methods for Retrieval Augmented Generation
- Matan Orbach
- Ohad Eytan
- et al.
- 2026
- AAAI 2026
I am a Research Staff Member at IBM Research, specializing in Retrieval-Augmented Generation (RAG). Over the last few years, I worked on a diverse set of NLP tasks, including key-point analysis, targeted sentiment analysis, and multilingual stance detection. Previously, I led a team within Project Debater (an IBM Grand Challenge) focused on generating rebuttals using principled arguments.
Prior to joining IBM, I received my M.Sc. in Electrical Engineering from the Technion in 2013, under the supervision of Prof. Koby Crammer. My research was on graph-based semi-supervised learning.