works on
adversarial training 1large language models 1prompt injection 1red teaming 1self-play 1

From the 1 of 7 linked papers with an AI index.

activity
20242026
most citedOpenAI GPT-5 System Card

17 citations · 17 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu +10

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instr…