Home
News
Members
Projects
Publications
Contact
Light
Dark
Automatic
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
Guy Bar-Shalom
,
Fabrizio Frasca
,
Derek Lim
,
Yoav Gelberg
,
Yftah Ziser
,
Ran El-Yaniv
,
Gal Chechik
,
Haggai Maron
January 2026
Machine Learning
Type
Conference paper
Publication
AAAI 2026
Large Language Models
Related
Analyzing Large Language Models by Learning on Token Distribution Sequences
Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
Cite
×