5 papers · 1 filter
Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities
Millicent Ochieng, Felermino D. M. A. Ali, Elizabeth A. Ankrah +8
In this paper, we examine how well AI-generated multimodal stories align with the lived practices, relationships, language, values, and visual expectations of the communities they…
Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts
Millicent Ochieng, Anja Thieme, Ignatius Ezeani +5
Sentiment analysis in low-resource, culturally nuanced contexts challenges conventional NLP approaches that assume fixed labels and universal affective expressions. We present a di…
MAIRA-2: Grounded Radiology Report Generation
Shruthi Bannur, Kenza Bouzid, Daniel C. Castro +18
Radiology reporting is a complex task requiring detailed medical image understanding and precise language generation, for which generative multimodal models offer a promising solut…
MAIRA-1: A specialised large multimodal model for radiology report generation
Stephanie L. Hyland, Shruthi Bannur, Kenza Bouzid +12
We present a radiology-specific multimodal model for the task for generating radiological reports from chest X-rays (CXRs). Our work builds on the idea that large language model(s)…
Exploring the Boundaries of GPT-4 in Radiology
Qianchu Liu, Stephanie Hyland, Shruthi Bannur +16
The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domai…