Cover Image

Multi-step retrieval and reasoning improves radiology question answering with large language models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wind, Sebastian, Sopa, Jeta, Truhn, Daniel, Lotfinia, Mahshad, Nguyen, Tri-Thien, Bressem, Keno, Adams, Lisa, Rusu, Mirabela, Köstler, Harald, Wellein, Gerhard, Maier, Andreas, Arasteh, Soroosh Tayebi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
by: Farajiamiri, Mina, et al.
Published: (2026)

Safety and accuracy follow different scaling laws in clinical large language models
by: Wind, Sebastian, et al.
Published: (2026)

Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
by: Mohammadi, Marziyeh, et al.
Published: (2025)

Cross-modal linkage risk in clinical vision-language models
by: Arasteh, Soroosh Tayebi, et al.
Published: (2026)

Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
by: Arasteh, Soroosh Tayebi, et al.
Published: (2026)

SteuerLLM: Local specialized large language model for German tax law analysis
by: Wind, Sebastian, et al.
Published: (2026)

RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering
by: Arasteh, Soroosh Tayebi, et al.
Published: (2024)

The role of self-supervised pretraining in differentially private medical image analysis
by: Arasteh, Soroosh Tayebi, et al.
Published: (2026)

Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
by: Lotfinia, Mahshad, et al.
Published: (2025)

Large Language Models Streamline Automated Machine Learning for Clinical Studies
by: Arasteh, Soroosh Tayebi, et al.
Published: (2023)

Differential privacy representation geometry for medical image analysis
by: Arasteh, Soroosh Tayebi, et al.
Published: (2026)

Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
by: Arasteh, Soroosh Tayebi, et al.
Published: (2023)

Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data
by: Arasteh, Soroosh Tayebi, et al.
Published: (2024)

From large language models to multimodal AI: A scoping review on the potential of generative AI in medicine
by: Buess, Lukas, et al.
Published: (2025)

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
by: Arasteh, Soroosh Tayebi, et al.
Published: (2025)

Perceptual implications of automatic anonymization in pathological speech
by: Arasteh, Soroosh Tayebi, et al.
Published: (2025)

From Text to Image: Exploring GPT-4Vision's Potential in Advanced Radiological Analysis across Subspecialties
by: Busch, Felix, et al.
Published: (2023)

AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
by: Mayr, Martin, et al.
Published: (2026)

Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs
by: Maier, Andreas, et al.
Published: (2026)

What Does DALL-E 2 Know About Radiology?
by: Adams, Lisa C., et al.
Published: (2022)

Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
by: Arasteh, Soroosh Tayebi, et al.
Published: (2023)

Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
by: Ma, Bole, et al.
Published: (2026)

CMRAG: Co-modality-based visual document retrieval and question answering
by: Chen, Wang, et al.
Published: (2025)

Optimizing open-domain question answering with graph-based retrieval augmented generation
by: Cahoon, Joyce, et al.
Published: (2025)

MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data
by: Han, Tianyu, et al.
Published: (2023)

Sex-based Bias Inherent in the Dice Similarity Coefficient: A Model Independent Analysis for Multiple Anatomical Structures
by: Häntze, Hartmut, et al.
Published: (2025)

BreastRegNet: A Deep Learning Framework for Registration of Breast Faxitron and Histopathology Images
by: Golestani, Negar, et al.
Published: (2024)

Can we repurpose multiple-choice question-answering models to rerank retrieved documents?
by: Catapang, Jasper Kyle
Published: (2025)

Enhancing textual textbook question answering with large language models and retrieval augmented generation
by: Alawwad, Hessa Abdulrahman, et al.
Published: (2024)

Enhancing scene‐text visual question answering with relational reasoning, attention and dynamic vocabulary integration
by: Mayank Agrawal, et al.
Published: (2024)

Towards a small language model powered chain‐of‐reasoning for open‐domain question answering
by: Jihyeon Roh, et al.
Published: (2024)

Mailbag questions and answers
by: Richard Rainsberger
Published: (2025)

100 questions answered?

Mailbag questions and answers
by: Richard Rainsberger
Published: (2025)

Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
by: Moll, Johannes, et al.
Published: (2025)

LongHealth: A Question Answering Benchmark with Long Clinical Documents
by: Adams, Lisa, et al.
Published: (2024)

Tables Guide Vision: Learning to See the Heart through Tabular Data
by: Hasny, Marta, et al.
Published: (2025)

Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
by: Wienholt, Patrick, et al.
Published: (2025)

Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering
by: Nachane, Saeel Sandeep, et al.
Published: (2024)

The Impact of Speech Anonymization on Pathology and Its Limits
by: Arasteh, Soroosh Tayebi, et al.
Published: (2024)