Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
Paper • 2611.05287 • Published • 1
Guido Freire
mollejasaurio
·
AI & ML interests
None yet
Recent Activity
liked a dataset 3 days ago
multi-objective-mo/clinical-mo-data authored a paper 4 days ago
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment upvoted a paper 4 days ago
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce MisalignmentOrganizations
upvoted a paper 4 days ago