LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Paper • 2410.02707 • Published • 47 •
5
Hadas Orgad
hadasor
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism submitted a paper 1 day ago
Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism upvoted a paper about 2 months ago
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric FactualityOrganizations
commented 2
papers over 1 year ago