5 papers
Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
Joakim Edin, Casper L. Christensen, Róbert Csordás +5
Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis. Mos…
Symphony for Medical Coding: A Next-Generation Agentic System for Scalable and Explainable Medical Coding
Joakim Edin, Andreas Motzfeldt, Simon Flachs +1
Medical coding translates free-text clinical documentation into standardized codes drawn from classification systems that contain tens of thousands of entries and are updated annua…
A medical coding language model trained on clinical narratives from a population-wide cohort of 1.8 million patients
Joakim Edin, Sedrah Butt Balaganeshan, Annike Kjølby Kristensen +3
Medical coding translates clinical documentation into standardized codes for billing, research, and public health, but manual coding is time-consuming and error-prone. Existing aut…
Code Like Humans: A Multi-Agent Solution for Medical Coding
Andreas Motzfeldt, Joakim Edin, Casper L. Christensen +3
In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce Code Like Humans: a new agentic framework for medical co…
Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability
Joakim Edin, Andreas Geert Motzfeldt, Casper L. Christensen +3
Deep neural network predictions are notoriously difficult to interpret. Feature attribution methods aim to explain these predictions by identifying the contribution of each input f…