yflantmy/universal-preference-hijacking-datasets
Viewer • Updated • 1.92k • 280
Yifan Lan
yflantmy
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation submitted a paper 1 day ago
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation upvoted a paper 5 months ago
Phi: Preference Hijacking in Multi-modal Large Language Models at
Inference TimeOrganizations
