conftrace_

explainable safety

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

safety detection (1) large language model (1) instruction tuning (1) explainable ai (1) text classification (1) adversarial robustness (1)

Papers

InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning EMNLP 2023