TukaBench extends JailbreakBench to African languages via human translation, cultural adaptation, curated prompts, and code-switching, finding lower refusal rates for culturally grounded prompts and surfacing comprehension and judging limitations.
In Findings of the Association for Computational Linguistics: ACL 2024, pages 9954– 9972, Bangkok, Thailand
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LASA improves LLM safety by aligning at language-agnostic semantic bottlenecks, reducing average ASR from 24.7% to 2.8% on LLaMA-3.1-8B and to 3-4% on Qwen models.
citing papers explorer
-
TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages
TukaBench extends JailbreakBench to African languages via human translation, cultural adaptation, curated prompts, and code-switching, finding lower refusal rates for culturally grounded prompts and surfacing comprehension and judging limitations.
-
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
LASA improves LLM safety by aligning at language-agnostic semantic bottlenecks, reducing average ASR from 24.7% to 2.8% on LLaMA-3.1-8B and to 3-4% on Qwen models.