AI RESEARCH
Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification
arXiv CS.LG
•
ArXi:2605.03091v1 Announce Type: new While pre-trained Transformer models achieve high accuracy on in-domain sentiment classification, they frequently experience severe performance degradation when transferring to out-of-domain data. We hypothesize that this generalization gap is driven by reliance on domain-specific spurious tokens. After nstrating that post-hoc-token-level attribution drift fails to predict this gap, we propose Attribution-Guided Masking (AGM), a