conftrace_

instruction hierarchy

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) prompt injection (2) constraint prioritization (1) rule following (1) safety protocol (1) model embedding (1) system prompt (1) behavioral prior (1) large language model alignment (1) security vulnerability (1)

Papers

Control Illusion: The Failure of Instruction Hierarchies in Large Language Models AAAI 2026 Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods EMNLP 2025 IHEval: Evaluating Language Models on Following the Instruction Hierarchy NAACL 2025 Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy ICLR 2025 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024