Fine-tuning LLMs on contradictory facts catastrophically corrupts unrelated knowledge, undeterred by selective neuron updates, while non-contradictory updates remain safe.
Continual learning with global prototypes: Beyond the scope of task supervision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
In Praise of Stubbornness: An Empirical Case for Cognitive-Dissonance Aware Continual Update of Knowledge in LLMs
Fine-tuning LLMs on contradictory facts catastrophically corrupts unrelated knowledge, undeterred by selective neuron updates, while non-contradictory updates remain safe.