Can AI Also Suffer Brain Damage? Study Reveals the Impact of Low-Quality Data on Large Language Models
The study found that after continuously exposing large language models to low-quality data (such as social media content), they can exhibit phenomena similar to human brain damage, leading to a 23% decline in reasoning ability and a 30% decline in long-term context memory. This damage is irreversible, and even subsequent training with high-quality data cannot fully restore it.