conftrace_

red teaming dataset

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

multilingual safety (1) large language model (1) false reject rate (1) multilingual llm (1) attack success rate (1) polish language (1) harmful content detection (1) red teaming (1) safety evaluation (1)

Papers

Rainbow-Teaming for the Polish Language: A Reproducibility Study NAACL 2025