conftrace_

adversarial probing

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) quantifier reasoning (1) adversarial prompting (1) generalized quantifier (1) adversarial benchmark (1) knowledge leakage (1) risk taxonomy (1) automated red teaming (1) misaligned behavior (1) multilingual nlu (1)

Papers

Anecdoctoring: Automated Red-Teaming Across Language and Place EMNLP 2025 Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models EMNLP 2025 Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction EMNLP 2024 Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks NAACL 2022