Tradeoffs Between Alignment and Helpfulness in Language Models with Representation Engineering
Paper • 2401.16332 • Published
Dorin Shteyman
DorinSht
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Why Fine-Tuning Encourages Hallucinations and How to Fix It upvoted a paper 9 months ago
Story2Board: A Training-Free Approach for Expressive Storyboard
Generation updated a model 10 months ago
loud-whisper-project/whistress_syntheticGPT_11k_2025_02_11__04_59_02Organizations
