SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Empirical tests on 148 images show that the best colorspace for k-means quantization depends on the image and the target number of colors k, with RGB winning in roughly half the cases.
citing papers explorer
-
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.
-
Optimized $k$-means color quantization of digital images in machine-based and human perception-based colorspaces
Empirical tests on 148 images show that the best colorspace for k-means quantization depends on the image and the target number of colors k, with RGB winning in roughly half the cases.