NVIDIA’s STEERLM Approach: Empowering User-Steerable Language Models

In a new paper SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF, an NVIDIA research team introduces STEERLM, a novel supervised fine-tuning method that empowers end-users to control model responses during inference, surpassing even state-of-the-art baselines, including RLHF models like ChatGPT-3.5.

ai art artificial intelligence chatgpt chatgpt-3.5 control deep-neural-networks fine-tuning inference language language models large language model machine learning machine learning & data science ml novel nvidia nvidia research paper research research team responses rlhf sft state supervised fine-tuning supervised learning team technology