HiPPrO generates counterspeech conditioned on both a strategy and an emotion via hierarchical prefix learning plus preference optimization, and reports gains on a new emotion-labeled corpus.
Grant SW, Hickey GL, Head SJ
3 Pith papers cite this work, alongside 471 external citations. Polarity classification is still indexing.
3
Pith papers citing it
471
external citations · Crossref
representative citing papers
Develops a restricted MCAR model via reparameterization to measure and control informativeness in multivariate spatial modeling of health events across subgroups.
BART analysis of PATH Waves 3-4 finds e-cigarette use has a null effect on smoking days among never-smoking adolescents and a diversionary effect among ever-smokers, eliminating the gateway effect reported by prior logistic regression models.
citing papers explorer
-
Restricted Multivariate Spatial Modeling
Develops a restricted MCAR model via reparameterization to measure and control informativeness in multivariate spatial modeling of health events across subgroups.
-
Logistic regression is not enough: The need for Bayesian nonparametric modelling for causal inference using observational data, exemplified by the 'gateway' effect
BART analysis of PATH Waves 3-4 finds e-cigarette use has a null effect on smoking days among never-smoking adolescents and a diversionary effect among ever-smokers, eliminating the gateway effect reported by prior logistic regression models.