Adding 96,679 human rationale highlights improves cancer-site classification less than adding the same number of full pathology reports, and the explainability gain is small.
Do Human Rationales Improve Machine Explanations?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Work on "learning with rationales" shows that humans providing explanations to a machine learning system can improve the system's predictive accuracy. However, this work has not been connected to work in "explainable AI" which concerns machines explaining their reasoning to humans. In this work, we show that learning with rationales can also improve the quality of the machine's explanations as evaluated by human judges. Specifically, we present experiments showing that, for CNN- based text classification, explanations generated using "supervised attention" are judged superior to explanations generated using normal unsupervised attention.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Can human clinical rationales improve the performance and explainability of clinical text classification models?
Adding 96,679 human rationale highlights improves cancer-site classification less than adding the same number of full pathology reports, and the explainability gain is small.