- ๐ธ Let's make sure AI is used for the common good!
- ๐ฑ Co-Director & Research Lead at Apart Research
- ๐ฑ looking to collaborate on AI research relevant to AI safety and AI alignment
- ๐ญ current research on safety evaluations of large language models
- ๐ญ previous research on text summarization, knowledge graph completion
- ๐ช community involvement: Vienna AI alignment group, European Network for AI Safety
jas-ho / contrastive-explanations Goto Github PK
View Code? Open in Web Editor NEWThis project forked from allenai/contrastive-explanations
Explaining neural decisions contrastively to alternative decisions.
License: Apache License 2.0