Pith. sign in

REVIEW 8 cited by

BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.10896 v1 pith:LB5BVT4K submitted 2025-06-12 cs.CL cs.AI

BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP

Thomas Sounack , Joshua Davis , Brigitte Durieux , Antoine Chaffin , Tom J. Pollard , Eric Lehman , Alistair E. W. Johnson , Matthew McDermott
show 2 more authors
Tristan Naumann Charlotta Lindvall
This is my paper
classification cs.CL cs.AI
keywords clinicalbiomedicalmodernbertbioclinicalencodersencoderlong-contextmodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Encoder-based transformer models are central to biomedical and clinical Natural Language Processing (NLP), as their bidirectional self-attention makes them well-suited for efficiently extracting structured information from unstructured text through discriminative tasks. However, encoders have seen slower development compared to decoder models, leading to limited domain adaptation in biomedical and clinical settings. We introduce BioClinical ModernBERT, a domain-adapted encoder that builds on the recent ModernBERT release, incorporating long-context processing and substantial improvements in speed and performance for biomedical and clinical NLP. BioClinical ModernBERT is developed through continued pretraining on the largest biomedical and clinical corpus to date, with over 53.5 billion tokens, and addresses a key limitation of prior clinical encoders by leveraging 20 datasets from diverse institutions, domains, and geographic regions, rather than relying on data from a single source. It outperforms existing biomedical and clinical encoders on four downstream tasks spanning a broad range of use cases. We release both base (150M parameters) and large (396M parameters) versions of BioClinical ModernBERT, along with training checkpoints to support further research.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. How much of an LLM-generated clinical corpus is actually new? A production-scale measurement of content redundancy for provenance classification

    cs.CL 2026-06 unverdicted novelty 7.0

    In a 2.51B-token LLM clinical extraction corpus, only 10.9% is trainable-unique while 79.4% is redundant from copying and duplication; de-duplication improves downstream disease recognition at fixed token budget.

  2. A Causal Language Modeling Detour Improves Encoder Continued Pretraining

    cs.CL 2026-05 conditional novelty 7.0

    A temporary CLM phase followed by MLM decay during encoder continued pretraining outperforms standard MLM on biomedical tasks by 0.3-2.8pp across languages and model sizes.

  3. Morphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction

    cs.CV 2026-06 unverdicted novelty 6.0

    A multimodal alignment framework derives morphology-aware image embeddings as continuous traits for Bayesian phylogenetic reconstruction, improving topological agreement on the Rove-Tree-11 dataset.

  4. TreeText-CTS: Compact, Source-Traceable Tree-Path Evidence for Irregular Clinical Time-Series Prediction

    cs.LG 2026-05 unverdicted novelty 6.0

    TreeText-CTS builds source-traceable tree-path evidence from multi-scale EHR windows via frozen XGBoost, selects subsets, and uses an LM encoder to reach top AUPRC among text-based interfaces on mortality and sepsis t...

  5. ShifaMind: A Multiplicative Concept Bottleneck for Interpretable ICD-10 Coding

    cs.LG 2026-05 unverdicted novelty 6.0

    ShifaMind achieves competitive performance with the LAAT baseline on MIMIC-IV top-50 ICD-10 coding while outperforming vanilla concept bottleneck models and providing concept-mediated explanations.

  6. SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification

    cs.CL 2026-05 unverdicted novelty 6.0

    SHIELD is a new diverse clinical note dataset paired with distilled small language models that achieve 0.89 span-level precision and 0.88 recall for on-premise PHI de-identification.

  7. SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification

    cs.CL 2026-05 conditional novelty 5.0

    SHIELD dataset and distilled DeBERTa v3 model achieve 0.88 micro precision and 0.86 recall on PHI de-identification while matching teacher performance on structured categories.

  8. Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings

    cs.LG 2026-04 unverdicted novelty 5.0

    LLM embeddings from clinical records, fused with tabular data via gradient-boosted trees, predict post-traumatic epilepsy at AUC-ROC 0.892 and AUPRC 0.798.