@article{alignmentbackfirelanguagedependentrevers, title = {Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems}, author = {Hiroki Fukui}, year = {2026}, eprint = {2603.04904}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.04904}, }