Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

This study investigates the cognitive gap in large language models where newly memorized facts during fine-tuning fail to generalize to downstream reasoning tasks.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.