DecSelfMask: New Method Uses Unlabeled Text to Improve Medical Classification Tasks
Researchers introduced DecSelfMask, a technique that leverages unlabeled clinical text to improve decoder-only language models on classification tasks, addressing the challenge of limited annotated data in medicine. The method uses relevance attribution to identify important portions of text, then creates self-supervised training examples by masking those sections and training models to reconstruct them. Testing on 1.9 million clinical notes showed significant improvements over standard approaches, with gains up to 19.9 points in macro F1 score.
DecSelfMask is a self-learning approach designed to enhance decoder-only model performance on classification tasks when annotated data is scarce—a common problem in medical domains. The technique combines relevance attribution methods with masking strategies: it identifies which portions of unlabeled text are task-relevant, then creates self-supervised training examples by masking those portions and training the model to reconstruct them via next-token prediction. The researchers evaluated DecSelfMask on 136 classification tasks drawn from 1.9 million clinical notes from an Italian hospital, testing it across five models of varying sizes and architectures. Results demonstrated consistent improvements, outperforming standard supervised fine-tuning by 19.9 macro F1 points, synthetic label generation by 12.5 points, and continual pretraining by 6.3 points. The approach also included probing analysis to understand model behavior.
What's missing
The paper does not discuss computational costs or training time comparisons with baseline methods. Generalization to non-clinical domains and non-English languages is not addressed. The study uses data from a single Italian hospital, which may limit geographic and institutional diversity.
What different sources said
- arXiv cs.CLCenter
DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.