Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs
Pratinav Seth, Saisab Sadhu, Anshul Kaushal +1
Methods for addressing safety drift in fine-tuned Large Language Models (LLMs) are scattered across incompatible implementations, lifecycle stages, and evaluation protocols, making…
cs.LG2026
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu
Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent wo…