Author

Matthias Keicher

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Mar 2026

Learning Diagnostic Reasoning for Decision Support in Toxicology

DeToxR (Decision-support for Toxicology with Reasoning), the first adaptation of Reinforcement Learning to emergency toxicology, is presented, which designs a robust data-fusion engine for multi-label prediction across 14 substance classes based on an LLM finetuned with Group Relative Policy Optimization (GRPO).

Nico Oberländer, D. Bani-Harouni, Tobias Zellner et al. · arXiv.org · 0 citations

#natural language process... Review Mar 2026

Calibrated Confidence Expression for Radiology Report Generation

ConRad (Confidence Calibration for Radiology Reports), a reinforcement learning framework for fine-tuning medical LVLMs to produce calibrated verbalized confidence estimates alongside radiology reports, is introduced and substantially improves calibration and outperforms competing methods.

D. Bani-Harouni, Chantal Pellegrini, Julian Lüers et al. · arXiv.org · 0 citations