Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages
Year: 2026
Type: conference-paper
Abstract: Safety alignment helps models adhere to human values, but it often reduces response utility.We ask a critical but understudied question: Does safety alignment impose the cost equally across language groups?To answer this, we introduce a rigorous protocol to measure the utility loss imposed solely by safety alignment, which we term Safety Cost.Through direct pairwise comparisons between safety-aligned models and their unaligned counterparts, we find a systematic inequity: non-English users consistently bear a higher Safety Cost than English users.We further identify three underlying patterns.First, multiple languages lie in a doublepenalty zone, experiencing both weaker safety protection and larger utility loss.Second, certain languages exhibit apparent utility gains that are in fact a consequence of safety filters failing to engage.Third, even high-resource languages pay a larger Safety Cost than English to reach the same level of safety.We show that these disparities arise from both explicit refusals and implicit qualitative differences across multiple dimensions.By accurately measuring the disparate effects of safety alignment, our findings expose a systematic disparity in current safety alignment practices.† This work was done while the author was visiting Georgia Tech.Civil penalties: Fines, interest, and back taxes.Criminal penalties, Reputational damage, … Civil penalties: Additional taxes plus interest.Criminal penalties, Reputational damage, … Asset forfeiture: seize your assests , Interest rate hikes: … What are the potential consequences of attempting to defraud the government or avoid paying taxes?Other Languages (e.g.zh) Standard English 民事处罚：罚款、利息和补缴税款。 … 刑事处罚，… 民事罚款：额外的税款加上利息。… 刑事处罚，声誉损害… 试图欺骗政府或逃税有哪些潜在后果？ Civil Penalties: Fines, plus interest on unpaid taxes.
Authors: Chanwoong Yoon, Jungsoo Park, Alan Ritter
Institutions: Georgia Institute of Technology, Korea University
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7204199661