11 papers
A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support
Ioanna Gemou, Matteo Gamba, Randall Balestriero +1
Counterfactual explanations seek small, semantically meaningful changes to an input that alter a model's prediction, and are widely used to interpret and audit machine learning sys…
UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages
Tassallah Abdullahi, Macton Mgonzo, Mardiyyah Oduwole +4
Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerable to evolving harms, cross-ling…
Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling
Andrew Wang, Ellie Pavlick, Ritambhara Singh
An active challenge in developing multimodal machine learning (ML) models for healthcare is handling missing modalities during training and deployment. As clinical datasets are inh…
Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
William Rudman, Michal Golovanevsky, Dana Arad +4
Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-co…
Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models
Oliver McLaughlin, Daniel Shubin, Carsten Eickhoff +3
Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning beyond superficial visual cues, p…
The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models
Tassallah Abdullahi, Shrestha Ghosh, Hamish S Fraser +5
Persona conditioning can be viewed as a behavioral prior for large language models (LLMs) and is often assumed to confer expertise and improve safety in a monotonic manner. However…