The reviewed record of science sign in
Pith

arxiv: 2206.02661 · v1 · pith:ETAEGF24 · submitted 2022-05-03 · cs.CL

Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild

Reviewed by Pithpith:ETAEGF24open to challenge →

classification cs.CL
keywords journalistscriticaldecompositiondeephumanmodelreliabilitytaylor
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.