3 papers
cs.CL2026
Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
Benjamin Warner, Ratna Sagari Grandhi, Max Kieffer +32
Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insufficient coverage of relevant…
cs.CL2025
It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers
Benjamin Clavié, Nathan Cooper, Benjamin Warner
While encoder-only models such as BERT and ModernBERT are ubiquitous in real-world NLP applications, their conventional reliance on task-specific classification heads can limit the…
cs.CL2024
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Benjamin Warner, Antoine Chaffin, Benjamin Clavié +11
Encoder-only transformer models such as BERT offer a great performance-size tradeoff for retrieval and classification tasks with respect to larger decoder-only models. Despite bein…