Melissa Kazemi Rad — accepted AI-conference papers

2026

DynaGuard: A Dynamic Guardian Model With User-Defined Policies

Monte Hoover, Vatsal Baherwani, Neel Jain, Khalid Saifullah, Joseph James Vincent, Chirag Jain +4

ICLR 2026poster

Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm categories, we introduce DynaGuard, a suite of dynamic guardian…

Cited by 0 Source ↗code ↗Scholar ↗

2025

GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection

Melissa Kazemi Rad, Alberto Purpura, Himanshu Kumar, Emily Chen, Mohammad Shahed Sorower

EMNLP 2025

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs) for dataset augmentation. GRAID consists of two stages: (i) ge

Cited by 0 Source ↗PDF ↗Scholar ↗