CG-CoT combines RAG and chain-of-thought prompting for Yoruba proverbs and reports higher cultural depth, but its accuracy result trails a baseline and no human evaluation supports the headline.
Boundary-weighted logit consistency improves calibration of segmentation networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Neural network prediction probabilities and accuracy are often only weakly-correlated. Inherent label ambiguity in training data for image segmentation aggravates such miscalibration. We show that logit consistency across stochastic transformations acts as a spatially varying regularizer that prevents overconfident predictions at pixels with ambiguous labels. Our boundary-weighted extension of this regularizer provides state-of-the-art calibration for prostate and heart MRI segmentation.
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages
CG-CoT combines RAG and chain-of-thought prompting for Yoruba proverbs and reports higher cultural depth, but its accuracy result trails a baseline and no human evaluation supports the headline.