RESEARCHInvestigateNEXT 12 MONTHS
Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers identify a 'comprehension-containment decoupling' where LLM safety alignment fails on low-resource language slurs.
Open source