Skip to content
conftrace_

Paul F Christiano

3 papers · 2017–2022 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+3 more ↓ πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Silver πŸ—ΊοΈ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird πŸ“› The Namer
πŸ‘₯ Mega-Team Β· Squad 🧭 Keyword Pioneer πŸ“ˆ Trend Setter

Venues

NeurIPS (3)

Top co-authors

Jan Leike (2) Jeffrey Wu (2) Long Ouyang (2) Ryan Lowe (2) Dario Amodei (2) Jacob Hilton (1) Alec Radford (1) Diogo Almeida (1) Maddie Simens (1) Shane Legg (1)

Research topics

Artificial Intelligence (2) Deep Learning (2) Machine Learning (2) Reinforcement Learning (2) Core AI (2) Learning Types Β· Deep Learning (2) Learning Types Β· Machine Learning (2) Methods (2) Natural Language Processing (1) Generation (1)

Keywords

preference learning (2) reinforcement learning (2) instruction following (1) language model alignment (1) reinforcement learning from human feedback (1) model alignment (1) reward function (1) human feedback (1) language model (1) reward model (1) supervised fine-tuning (1) human preference (1) deep reinforcement learning (1) trajectory segment (1) reward modeling (1)

Papers

Training language models to follow instructions with human feedback NeurIPS 2022 Learning to summarize with human feedback NeurIPS 2020 Deep Reinforcement Learning from Human Preferences NeurIPS 2017