AIConfPaper
← Search

Daniel C. Castro

7 accepted papers

2025

Balancing Act: Diversity and Consistency in Large Language Model Ensembles

Ahmed Abdulaal, Chen Jin, Nina Montaña-Brown, Aryo Pradipta Gema, Daniel C. Castro, Daniel C. Alexander +4
ICLR 2025poster

Ensembling strategies for Large Language Models (LLMs) have demonstrated significant potential in improving performance across various tasks by combining the strengths of individual models. However, identifying the most effective ensembling method remains an open challenge, as neither maximizing out…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Rethinking Fair Representation Learning for Performance-Sensitive Tasks

Charles Jones, Fabio De Sousa Ribeiro, Mélanie Roschewitz, Daniel C. Castro, Ben Glocker
ICLR 2025poster

We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions inherent to these methods. We prove fundamental limitations on fair representatio…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning

Ahmed Abdulaal, adamos hadjivasiliou, Nina Montana-Brown, Tiantian He, Ayodeji Ijishakin, Ivana Drobnjak +2
ICLR 2024poster

Scientific discovery hinges on the effective integration of metadata, which refers to a set of 'cognitive' operations such as determining what information is relevant for inquiry, and data, which encompasses physical operations such as observation and experimentation. This paper introduces the Causa…

Cited by 15Source ↗PDF ↗Scholar ↗
2023

Exploring the Boundaries of GPT-4 in Radiology

Qianchu Liu, Stephanie Hyland, Shruthi Bannur, Kenza Bouzid, Daniel C. Castro, Maria Teodora Wetscherek +13
EMNLP 2023long main

The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the…

Cited by 0Source ↗Scholar ↗
2023

Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing

Shruthi Bannur, Stephanie Hyland, Qianchu Liu, Fernando Pérez-García, Maximilian Ilse, Daniel C. Castro +10
CVPR 2023poster

Self-supervised learning in vision--language processing (VLP) exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not onl…

Cited by 139Source ↗PDF ↗Scholar ↗
2023

Measuring axiomatic soundness of counterfactual image models

Miguel Monteiro, Fabio De Sousa Ribeiro, Nick Pawlowski, Daniel C. Castro, Ben Glocker
ICLR 2023poster

We present a general framework for evaluating image counterfactuals. The power and flexibility of deep generative models make them valuable tools for learning mechanisms in structural causal models. However, their flexibility makes counterfactual identifiability impossible in the general case. Motiv…

Cited by 25Source ↗PDF ↗Scholar ↗
2022

Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing

Benedikt Boecking, Naoto Usuyama, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Stephanie Hyland +6
ECCV 2022poster

"Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision-language modelling compared to…

Cited by 306Source ↗PDF ↗code ↗Scholar ↗