Research

Most recent publications on Google Scholar.

Multi-module GRPO: Composing policy gradients and prompt optimization for language model programs

Noah Ziems, Dilara Soylu, Lakshya A Agrawal, Isaac Miller, Liheng Lai, Chen Qian, Kaiqiang Song, Meng Jiang, Dan Klein, Matei Zaharia, Karel D'Oosterlinck, Christopher Potts, Omar Khattab

Preprint

paper code

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Omar Khattab, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
Preprint
paper code

TOWER: Tree Organized Weighting for Evaluating Complex Instructions
Noah Ziems, Zhihan Zhang, Meng Jiang
EMNLP 2024
paper code

Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks

Noah Ziems, Annalisa Szymanski, Heather A Eicher-Miller, Toby Jia-Jun Li, Meng Jiang, Ronald A Metoyer

IUI 2024

paper

Explaining Tree Model Decisions in Natural Language for Network Intrusion Detection
Noah Ziems, Gang Liu, John Flanagan, Meng Jiang
NeurIPS XAIA Workshop 2023
paper code

Large Language Models are Built-in Autoregressive Search Engines
Noah Ziems, Wenhao Yu, Zhihan Zhang, Meng Jiang
ACL Findings 2023
paper code

Embedding Mental Health Discourse for Community Recommendation

Hy Dang, Bang Nguyen, Noah Ziems, Meng Jiang

ACL CODI Workshop 2023

Parathyroid Tumor Detection with Machine Learning

Noah Ziems, Jim Norman, Shaoen Wu

IEEE Globecom 2021

Security Vulnerability Detection Using Natural Language Processing

Noah Ziems, Shaoen Wu

IEEE Infocom 2021