Tag
This paper studies how pruning attention layers in LLMs affects explanation faithfulness and confidence calibration, finding that accuracy often remains high but interpretability and reliability degrade, highlighting a misalignment between model confidence, interpretability, and accuracy.
An empirical study investigating how long, semantically dense benign text can shift a model's latent space trajectory, diluting initial system prompts and bypassing post-training alignment constraints, as observed in both closed and open-source models.