SOURCE-LINKED INTELLIGENCE

Popular Knowledge Propagates More Errors in LLM Knowledge Updating

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Updating a language model's knowledge through fine-tuning is essential for keeping its outputs current, yet can also induce factual forgetting and new hallucinations. Prior work shows that long-tail knowledge is harder to acquire and newly memorized long-tail facts are difficult to retain during later fine-tuning. We study a complementary question: among facts that a model has encoded correctly, which are most vulnerable to collateral corruption during other updates? To investigate this question under a realistic factual distribution, we construct a large-scale graph FACTPROP of verified Wikip

Read original source ↗ Open in workspace

recordType

paper

region

Global