Steering Gemini using BIDPO vectors
DeepMind reports that BIDPO-trained steering vectors boosted TruthfulQA in Gemini 1.5 but failed to beat stronger prompt-based baselines after a model update, so the project ended.
Research / Sources
Google DeepMind Safety Research
Safety research from Google DeepMind. deepmindsafetyresearch.medium.com
Responsibility & Safety (19)ai (1)ai-assistance (1)ai-training (1)alignment-problem (1)amplified-oversight (1)complementarity (1)google-gemini (1)hybridization (1)jailbreak (1)language-model (1)sycophancy (1)