Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback
Adam Dahlgren Lindström, Leila Methnani, Lea Krause, Petter Ericson, Íñigo Martínez de Rituerto de Troya, Dimitri Coelho Mollo, Roel Dobbe
De quem é
- Vrije Universiteit Amsterdamafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- Safe testingCentrum Wiskunde & Informatica · 363 citações
- MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMsVrije Universiteit Amsterdam · 172 citações
- The key artificial intelligence technologies in early childhood education: a reviewVrije Universiteit Amsterdam · 154 citações