# Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification

arXiv: https://arxiv.org/abs/2605.03091 · HTML: https://mlsanity.com/paper/2605.03091/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)

## Abstract (arXiv)

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 demonstrating that post-hoc-token-level attribution drift fails to predict this gap, we propose Attribution-Guided Masking (AGM), a training time intervention that dynamically detects and penalizes highly attributed spurious tokens during fine-tuning. AGM's core component is a gradient based attribution masking loss (Lmask), which can optionally be combined with a counterfactual contrastive loss to enforce domain-invariant representations, all without requiring target-domain labels or human annotation. Evaluated in a strict zero-shot transfer setting across four diverse domains with eight random seeds, AGM achieves competitive generalization compared to five strong baselines on the hardest transfer (Sentiment140): Delta = 0.244 versus DANN (0.264), DRO (0.248), Fish (0.247), and IRM (0.238), while uniquely providing token-level interpretability into which features drive the generalization gap. Our qualitative analysis confirms that AGM suppresses attribution on domain-specific tokens such as @mentions, hashtags, and slang, shifting reliance toward domain-invariant sentiment markers. Our ablation study further confirms that attribution-guided masking is the critical component: removing it or replacing it with random token selection consistently degrades performance on difficult transfers.