PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Researchers develop a human-centered approach to align AI agents with privacy norms by creating a comprehensive dataset of privacy judgments and using annotation-conditioned reward…
Hugging Face · Daily Papers
·Manveer Singh Tamber, Abhay Puri
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet, Perouz Taslakian, Jimmy Lin, Spandana Gella
- 3 upvotes da comunidade
- Temas: privacy alignment, large language models, reward modeling, annotation-conditioned reward modeling, human judgment, privacy norms
Resumo
Resumo original (em inglês), extraído do paper:
Researchers develop a human-centered approach to align AI agents with privacy norms by creating a comprehensive dataset of privacy judgments and using annotation-conditioned reward modeling to improve agent behavior.Onde ler
// relacionados
