KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
Harold Ngabo-Woods, Larisa Dunai, and Isabel Seguí Verdú
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Mental health AI safety evaluations must preserve temporal evidence from interaction sequences rather than isolated responses, as current protocols create non-identifiable safety properties according to the introduced Temporal Safety Non-Identifiability concept and SCOPE-MH standard.
citing papers explorer
No citing papers match the current filters.