The paper introduces CHIP 2026 Shared Task 1, which focuses on patient‑specific phenotype concept recognition in full‑text biomedical literature. The task is split into two subtasks—full‑text phenotype concept recognition and patient‑specific phenotype association—using 200 annotated articles from the PatientPheX dataset that include 506 patients, 15,193 phenotype mentions, and 5,656 patient‑phenotype associations. A large community of 455 teams participated, with the best system scoring 0.7389, surpassing the baseline by 8.37 percentage points, and demonstrating the effectiveness of biomedical language models, large language models, and ensemble strategies while highlighting ongoing challenges in patient attribution and phenotype normalization.
arXiv:2606. 19345v1 Announce Type: cross Abstract: The rapid increase in scientific publications leads to the fact that manual study screening in systematic literature reviews (SLRs) is increasingly resource consuming, inefficient, and inconsistent.
This study benchmarks transformer models for Bangla medical named entity recognition (NER), comparing BanglaBERT, multilingual BERT (mBERT), XLM‑RoBERTa, and GPT‑4o mini under zero‑shot and few‑shot prompting. Across a full test set of 3,179 samples, fine‑tuned XLM‑RoBERTa achieves a new state‑of‑the‑art F1‑score of 0.5959, while BanglaBERT lags with 0.4937, suggesting that domain diversity outweighs language specificity. The analysis shows high performance on Medicine and Specialist entities (F1 > 0.83) but lower accuracy on Symptoms (F1 0.4367), and demonstrates that fine‑tuned transformers outperform prompt‑only approaches by a factor of 3.76.
The paper introduces Distilled Rapid Embedding Transfer (DRET), a parameter‑efficient method that injects biomedical domain knowledge from large specialized models into a smaller general‑purpose model without retraining on the original specialized corpora. DRET evolves through iterative strategies—tokenizer‑merge (DRET 1.x), hybrid embedding averaging (DRET 2.0), priority‑based embedding transfer (DRET 3.x), and further refinements (DRET 4.x)—and demonstrates that a 66‑million‑parameter DistilBERT can achieve competitive or superior performance on token‑level PICO classification compared to much larger models, while remaining lightweight. The authors validate the embedding‑level transfer with cosine similarity, semantic‑shift, and t‑SNE analyses, highlighting DRET’s potential for scalable, resource‑efficient biomedical text mining.
arXiv:2605.20197v2 Announce Type: replace Abstract: Medical concept extraction from electronic health records underpins many downstream applications, yet remains challenging because medically meaning...
arXiv:2609.19071v1 Announce Type: new Abstract: Extracting SNP-phenotype associations from biomedical literature is vital but challenging. We benchmarked diverse NLP models, including MLMs, hybrid ar...
arXiv:2603. 13673v2 Announce Type: replace Abstract: Accurate extraction of Alzheimer's Disease and Related Dementias (ADRD) phenotypes from electronic health records (EHR) is critical for early-stage detection and disease staging.
This thesis explores how to select and adapt NLP models for global health literature when annotated data and computational resources are scarce. It compares skip‑gram word2vec models trained on increasingly large specialized corpora with BioWordVec for semantic tag discovery, finding that larger coverage does not always yield more useful domain associations. The study also evaluates convolutional spaCy models versus a RoBERTa transformer for named entity recognition, noting a trade‑off between higher F1 scores and longer inference time, and investigates MiniLM few‑shot versus BART‑MNLI zero‑shot classification for multi‑label topic classification, highlighting practical constraints of inference cost. "whyItMatters":"The work provides empirical guidance on balancing model accuracy and resource demands for building knowledge systems in low‑resource global health settings."
The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.
EHRAdapt is an adapter that maps electronic health record tuples directly into a frozen language model’s embedding space, using learned embeddings for modality, time gaps, and dedicated vectors for event codes. It represents each event vector as a sum of a frozen, ontology‑trained semantic prior and a low‑rank evidence residual, enabling robust learning even for rare clinical events. Experiments on four million patient records with three large language model backbones show that the full adapter outperforms all ablations in next‑event prediction and improves rare‑disease discrimination in classification tasks.
arXiv:2606. 13051v1 Announce Type: new Abstract: Despite advances in information extraction driven by deep learning and large language models, performance gaps remain in highly specialized biomedical fields, where domainspecific complexity poses challenges for generalist models.
CardioLM introduces a multilingual suite of small language models tailored for cardiology, comprising CardioBERTa encoders and CardioNER NER models trained on the CardioCCC corpus of 508 cardiology case reports translated into seven languages. The study shows that specialty‑specific pretraining reduces pseudo‑perplexity significantly but only marginally improves strict span‑level F1, whereas joint multilingual training with XLM‑RoBERTa‑large yields the best F1 scores across languages and entity types. Clinicians rated CardioNER far superior to rule‑based baselines, indicating practical value for multi‑country clinical information extraction.
arXiv:2609.15713v1 Announce Type: new Abstract: Recent approaches to 30-day hospital readmission prediction rely on pre-trained language models applied to discharge summaries. Although these methods...