I’m Pegah Jandaghi, a final-year PhD candidate in Computer Science at the University of Southern California. I’m advised by Prof. Morteza Dehghani. I also collaborate closely with Robin Jia.

My research focuses on Transfer Learning, Dialog Systems, and Large Language Models (LLMs). I’m particularly interested in making LLMs more personalized, specialized, and accessible—especially for non-experts. I’m passionate about advancing techniques that help adapt and evaluate LLMs effectively across domains, enabling broader accessibility and usability for diverse applications.

Work Experience

• Research Intern @ Microsoft, Summer 2025
  
  • Supervisor: Bahareh Sarrafzadeh
• Graduate Student Researcher @ Google Research, Fall 2022 - Spring 2023
  
  • Supervisor: Hakim Sidahmed

Selected Publications

• A Systematic Analysis of Base Model Choice for Reward Modeling
  K Ahrabian, P Jandaghi, N Mokhberian, P Karimireddy, J Pujara

• Faithful Persona-based Conversational Dataset Generation with Large Language Models
  P Jandaghi, X Sheng, X Bai, J Pujara, H Sidahmed
  In Findings of the Association for Computational Linguistics: ACL 2024

• Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality
  P Zhou, H Cho, P Jandaghi, DH Lee, B Lin, J Pujara, X Ren
  In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

• FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue
  A Albalak, YL Tuan, P Jandaghi, C Pryor, L Yoffe, D Ramachandran, L Getoor, J Pujara, W Wang
  In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing