Model techniques map
Techniquespost-trainingsupervised fine-tuning

specific method · filed under post-training

Adversarial fine-tuning

Fine-tuning applied adversarially to assess whether a model can reach high capability in specified evaluation categories.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we created adversarially fine-tuned versions of gpt-oss-120b for the two categories in which we believed there was a plausible chance that adversarial fine-tuning might allow the model to reach High capability under our framework

usedevaluation onlyin gpt-oss-120bOpenAI

Filed alongside

Other methods under post-training :: supervised fine-tuning.