On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
Paper • 2502.14296 • Published • 45
Haoran Wang
wang2226
AI & ML interests
Reasoning, Inference-time Intervention, Safety
Recent Activity
updated a Space about 4 hours ago
wang2226/beyond-tokens-decoding published a Space about 4 hours ago
wang2226/beyond-tokens-decoding updated a Space about 6 hours ago
wang2226/steering-showcaseOrganizations
upvoted a paper over 1 year ago
upvoted an article about 2 years ago
Article
How to generate text: using different decoding methods for language generation with Transformers
patrickvonplaten
• • 309 upvoted a paper over 2 years ago