About Me

I’m Pegah Jandaghi, a final-year PhD candidate in Computer Science at the University of Southern California. I’m advised by Prof. Jay Pujara and work as part of the JAUNTS lab. 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.

Education

• Ph.D. in Computer Science, University of Southern California, 2025 (expected)
• M.S. in Computer Science, University of Southern California, 2019
• B.Sc. in Computer Engineering, Sharif University of Technology, 2017
• B.Sc. in Mathematics and Applications, Sharif University of Technology, 2017

Working Experience

• Graduate Student Researcher @ Google Research, Fall 2022 - Spring 2023
  Supervisor: Hakim Sidahmed

• Student Researcher @ Center on Knowledge Graphs (USC/ISI), Fall 2017 - Spring 2019
  Supervisor: Jay Pujara

• Summer Intern @ Fanap ICT, Summer 2016
  Supervisor: Ali Salehi

Preprints

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

• T-Measure: A Measure for Model Transferability
  P Jandaghi, P Zhou, A Albalak, J Pujara

• Emotion Recognition in Conversation using Probabilistic Soft Logic
  E Augustine, P Jandaghi, A Albalak, C Pryor, C Dickens, W Wang, L Getoor

Selected Publications

• Trim My View: An LLM-Based Code Query System for Module Retrieval in Robotic Firmware
  S Arasteh, P Jandaghi, N Weideman, D Perepech, M Raghothaman, C Hauser, L Garcia
  In Proceedings of the Workshop on Binary Analysis Research (BAR@NDSS 2025)

• 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

• Identifying Quantifiably Verifiable Statements from Text
  P Jandaghi, J Pujara
  In Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING@ ACL 2023)

• 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

• Probing Commonsense Explanation in Dialogue Response Generation
  P Zhou, P Jandaghi, H Cho, B Lin, J Pujara, X Ren
  In Findings of the Association for Computational Linguistics: EMNLP 2021

• QANet: Tensor Decomposition Approach for Query-Based Anomaly Detection in Heterogeneous Information Networks
  V Ranjbar, M Salehi, P Jandaghi, M Jalili
  In IEEE Transactions on Knowledge and Data Engineering

Teaching and Services

• Teaching Assistant for CSCI 270: Introduction to Algorithms and Theory of Computing, USC, Fall 2023, Spring 2025
• Teaching Assistant for CSCI 103: Introduction to Programming, USC, Fall 2024,
• Teaching Assitant for CSCI 170: Discrete Methods in Computer Science, USC, Spring 2024
• Teaching Assistant for CS 570: Analysis of Algorithms, USC, Fall 2022, Spring 2023

• Reviewer for KDD 2024, AAAI 2023
• USC Women in Science and Engineering (WiSE) PhD mentor 2023-2024