BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs

arXiv:2512.22174v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hardware degradation, cosmic radiation, or deliberate fault-injection attacks such as Rowhammer. These faults silently corrupt internal parameters and can lead to unpredictable or dangerous model behavior. Localizing these corruptions is essential: without identifying the affected region, it is impossib