Yftah Ziser

Latest

• Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
• A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs
• Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
• Iterative Multilingual Spectral Attribute Erasure
• Policy Optimized Text-to-Image Pipeline Design
• TSPRank: Bridging Pairwise and Listwise Methods with a Bilinear Travelling Salesman Model
• Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
• Analyzing Large Language Models by Learning on Token Distribution Sequences