collaborators

11 papers

cs.CL2026

Learning Diagnostic Reasoning for Decision Support in Toxicology

Nico Oberländer, David Bani-Harouni, Tobias Zellner +3

Acute poly-substance intoxication requires rapid, life-saving decisions under substantial uncertainty, as clinicians must rely on incomplete ingestion details and nonspecific sympt…

cs.CL2026

Calibrated Confidence Expression for Radiology Report Generation

David Bani-Harouni, Chantal Pellegrini, Julian Lüers +6

Safe deployment of Large Vision-Language Models (LVLMs) in radiology report generation requires not only accurate predictions but also clinically interpretable indicators of when o…

cs.LG2026

EHR2Path: Comprehensive Pathway-Level Modeling of Longitudinal Patient Trajectories from Multimodal Electronic Health Records

Chantal Pellegrini, Ege Özsoy, David Bani-Harouni +2

Forecasting how a patient's condition is likely to evolve, including possible deterioration, recovery, treatment needs, and care transitions, could support more proactive and perso…

cs.AI2026

Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting

Chantal Pellegrini, Adrian Delchev, Ege Özsoy +2

Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decis…

cs.CL2026

Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement Learning

David Bani-Harouni, Chantal Pellegrini, Ege Özsoy +2

Clinical decision-making is a dynamic, interactive, and cyclic process where doctors have to repeatedly decide on which clinical action to perform and consider newly uncovered info…

cs.CL2026

Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models

David Bani-Harouni, Chantal Pellegrini, Paul Stangel +4

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that a…