conftrace_

instruction-following model

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prompt hijacking (1) prompt injection attack (1) prompt extraction (1) bias measurement (1) gender bia (1) social bia (1) language model (1) benchmark dataset (1)

Papers

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game ICLR 2024 Measuring bias in Instruction-Following models with P-AT EMNLP 2023