Global ETD Search

Beyond pre-training: continual learning and hallucinations in transformer-based language models.

Suresh, Malavika2026

… is determined without access to the data. Based on this, a novel method is developed that takes into account the relative importance of model parameters across old and new tasks for regularising the model training more effectively. The proposed method is evaluated on various continual …

rgu Repository record for Beyond pre-training: continual learning and hallucinations in transformer-based language models. (opens in a new tab)