RL-MIA

Emerging

1papers using it

2025first seen

RL-MIA is a benchmark designed to simulate data contamination scenarios in Reinforcement Learning post-training for evaluating the reliability of Large Language Models.

🔎 Find this dataset

Papers using RL-MIA (1)

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models2025

RL-MIA dataset — papers, benchmarks & downloads · Large Language Models