arxiv:2603.09906
Mor Geva
mega
AI & ML interests
None yet
Recent Activity
upvoted a paper about 10 hours ago
Hallucinations Undermine Trust; Metacognition is a Way Forward authored a paper about 2 months ago
Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models authored a paper about 2 months ago
From Directions to Regions: Decomposing Activations in Language Models via Local GeometryOrganizations
models 0
None public yet
datasets 0
None public yet