Skip to content
conftrace_

explainability technique

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model bia (2) user feature (1) gradient-based explanation (1) transformer model (1) time-frequency representation (1) graph neural network (1) neural network (1) abstract rule (1) layer integrated gradient (1) artifact region (1)

Papers

A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations Interspeech 2025 Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes ICML 2025 A Fine Line Between Irony and Sincerity: Identifying Bias in Transformer Models for Irony Detection ACL 2023 Understanding and Interpreting the Impact of User Context in Hate Speech Detection NAACL 2021 A Diagnostic Study of Explainability Techniques for Text Classification EMNLP 2020