Existing LLM unlearning methods struggle with robustness: unbounded forget losses degrade model coherence, fixed-weight balancing cannot adapt as retain difficulty shifts mid-training, and methods that work on one benchmark falter under scaling or repeated application. We propose BLADE, a constrained bilevel framework...
Md Toufikuzzaman, Ahmad Mousavi, Dongwon Lee· 0 citations
RareTrap provides model developers a principled approach for evaluating language models under a common distribution, and prioritizing alignment effort to improve safety and mitigate risks.
Elsayed Eshra, Ali Al-Lawati, Dongwon Lee et al.· 0 citations
RoSh is proposed, a per-language shift and rotation of the residual stream, computed in closed form at three layers, with no training and no weight modified, that improves every model and closes 75% of the gap on average, helping most where the model was worst.
Muhammad Ahmad, Fatemeh Seyedin, Adrian Weller et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.