Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild
This addresses the need for practical reliability assessment in journalism, though it is incremental as it applies an existing method to a new domain.
The study tackled the problem of evaluating model interpretability methods in real-world settings by testing Deep Taylor Decomposition with journalists assessing news reliability, resulting in faster and better human decision-making and a more critical attitude toward sources.
We argue that we need to evaluate model interpretability methods 'in the wild', i.e., in situations where professionals make critical decisions, and models can potentially assist them. We present an in-the-wild evaluation of token attribution based on Deep Taylor Decomposition, with professional journalists performing reliability assessments. We find that using this method in conjunction with RoBERTa-Large, fine-tuned on the Gossip Corpus, led to faster and better human decision-making, as well as a more critical attitude toward news sources among the journalists. We present a comparison of human and model rationales, as well as a qualitative analysis of the journalists' experiences with machine-in-the-loop decision making.