#instruction-hierarchy2 articles

2 articles

AIBullisharXiv – CS AI · 2d ago7/10

🧠

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

OpenAI researchers introduce IH-Challenge, a reinforcement learning dataset designed to improve instruction hierarchy in frontier LLMs. Fine-tuning GPT-5-Mini with this dataset improved robustness by 10% and significantly reduced unsafe behavior while maintaining helpfulness.

🏢 OpenAI🏢 Hugging Face🧠 GPT-5

AIBullishOpenAI News · 3d ago7/10

🧠

Improving instruction hierarchy in frontier LLMs

A new training method called IH-Challenge has been developed to improve instruction hierarchy in frontier large language models. The approach helps models better prioritize trusted instructions, enhancing safety controls and reducing vulnerability to prompt injection attacks.