works on
adapter training 1backdoor mitigation 1inoculation prompting 1large language models 1selective generalization 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time

Daniel Tan, Anders Woodruff, Niels Warncke +4

Language model finetuning often results in learning undesirable traits in combination with desired ones. To address this, we propose inoculation prompting: modifying finetuning dat…