4.3k citations · 7.2k across the 45 of their papers we have counts for
3 papers · 1 filter
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner +9
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate wh…
Let's Verify Step by Step
Hunter Lightman, Vineet Kosaraju, Yura Burda +7
In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state-of-the-art models still regularly produce…
GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler +278
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-wor…