# Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations

arXiv: https://arxiv.org/abs/2605.11502 · HTML: https://mlsanity.com/paper/2605.11502/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 21 of 21)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://mlsanity.com/paper/2211.13308/) (2022)
- [The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?](https://mlsanity.com/paper/2010.05607/) (2020)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals](https://mlsanity.com/paper/2012.10040/) (2020)
- [Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategies](https://mlsanity.com/paper/2102.08366/) (2021)
- [Understanding Contrastive Learning via Distributionally Robust Optimization](https://mlsanity.com/paper/2310.11048/) (2023)
- [Heterogeneous Contrastive Learning](https://mlsanity.com/paper/2105.09401/) (2021)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics](https://mlsanity.com/paper/2302.09344/) (2023)
- [Measuring the Robustness of NLP Models to Domain Shifts](https://mlsanity.com/paper/2306.00168/) (2023)
- [On Adversarial Examples for Biomedical NLP Tasks](https://mlsanity.com/paper/2004.11157/) (2020)
- [Improving the robustness and accuracy of biomedical language models through adversarial training](https://mlsanity.com/paper/2111.08529/) (2021)
- [Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy](https://mlsanity.com/paper/2501.09086/) (2025)

## Abstract (arXiv)

Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowledge discovery. Prior work on automated publication type and study design indexing has primarily focused on expanding label coverage, enriching feature representations, and improving in-domain accuracy, with evaluation typically conducted on data drawn from the same distribution as training. Although pretrained biomedical language models achieve strong performance under these settings, models optimized for in-domain accuracy may rely on superficial lexical or dataset-specific cues, resulting in reduced robustness under distributional shift. In this study, we introduce an evaluation framework based on controlled semantic perturbations to assess the robustness of a publication type classifier and investigate robustness-oriented training strategies that combine entity masking and domain-adversarial training to mitigate reliance on spurious topical correlations. Our results show that the commonly observed trade-off between robustness and in-domain accuracy can be mitigated when robustness objectives are designed to selectively suppress non-task-defining features while preserving salient methodological signals. We find that these improvements arise from two complementary mechanisms: (1) increased reliance on explicit methodological cues when such cues are present in the input, and (2) reduced reliance on spurious domain-specific topical features. These findings highlight the importance of feature-level robustness analysis for publication type and study design classification and suggest that refining masking and adversarial objectives to more selectively suppress topical information may further improve robustness. Data, code, and models are available at: https://github.com/ScienceNLP-Lab/MultiTagger-v2/tree/main/ICHI