Sebastian Farquhar
3 papers in the PaperMetrix corpus
Papers by this author
-
Discovering Agents
2022 · arXiv (Cornell University)
Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial -- often the causal model is just assumed by the modeler without much justification …
-
CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models
2022 · arXiv (Cornell University)
Users often ask dialogue systems ambiguous questions that require clarification. We show that current language models rarely ask users to clarify ambiguous questions and instead provide incorrect answers. To address this, we introduce CLAM: a …
-
Holistic Safety and Responsibility Evaluations of Advanced AI Models
2024 · arXiv (Cornell University)
Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set …