6 papers
When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
Mattia Carletti, Edward Phillips, Fredrik K. Gustafsson +5
Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide conflicting evidence. We study…
Geometric Characterisation and Structured Trajectory Surrogates for Clinical Dataset Condensation
Pafue Christy Nganjimi, Andrew Soltan, Danielle Belgrave +3
Dataset condensation constructs compact synthetic datasets that retain the training utility of large real-world datasets, enabling efficient model development and potentially suppo…
Democratising Clinical AI through Dataset Condensation for Classical Clinical Models
Anshul Thakur, Soheila Molaei, Pafue Christy Nganjimi +5
Dataset condensation (DC) learns a compact synthetic dataset that enables models to match the performance of full-data training, prioritising utility over distributional fidelity.…
Improving Clinical Dataset Condensation with Mode Connectivity-based Trajectory Surrogates
Pafue Christy Nganjimi, Andrew Soltan, Danielle Belgrave +3
Dataset condensation (DC) enables the creation of compact, privacy-preserving synthetic datasets that can match the utility of real patient records, supporting democratised access…
Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
Edward Phillips, Sean Wu, Soheila Molaei +3
Large language models are known to hallucinate, generating linguistically plausible but incorrect answers to questions. Uncertainty quantification has been proposed as a strategy t…
Aggregation on Learnable Manifolds for Asynchronous Federated Optimization
Archie Licudi, Anshul Thakur, Soheila Molaei +2
Asynchronous federated learning (FL) with heterogeneous clients faces two key issues: curvature-induced loss barriers encountered by standard linear parameter interpolation techniq…