Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models

arXiv:2611.06553 · cs.AI, cs.CR · Submitted 2026-11-04 · Read on arXiv

cs.AI, cs.CR

Submitted: 2026-11-04

Updated: 2026-11-04

Code: https://github.com/meta-llama/llama3

Terminology

Sources

Related papers