Papers by Melissa Kazemi Rad
GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are expensive to run within a large-scale system and not ideal for low-latency use cases. |
| Approach: | They propose a pipeline that leverages Large Language Models (LLMs) for dataset augmentation. |
| Outcome: | The proposed pipeline improves the performance of a harmful text classification dataset using Large Language Models (LLMs). |