works on
adapter training 1backdoor mitigation 1bias 1ethical AI 1inoculation prompting 1large language models 1LLM evaluation 1model alignment 1selective generalization 1value leakage 1

From the 2 of 5 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors

Maxime Riché, Daniel Tan, Vili Kohonen +1

The paper proposes inoculation adapters, a LoRA‑based method that trains on undesired traits and then discards the adapter to improve selective generalization of desired capabiliti…