Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Prompt-based personalization cannot fix cultural bias: steering LLMs with cultural context actually widens the disparity between dominant and underrepresented cultures, even when injecting explicit cultural facts.
Up to 78 percentage points of reported machine unlearning success can be reversed with just 10 unlabeled images and zero weight updates, exposing widely cited forgetting benchmarks as mere BatchNorm illusions.
