4 papers
Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept
Samuele Punzo, Giovanni CinÃ, Sandro Pezzelle
Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex selectional constraints and contex…
Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure
Davide Tugnoli, Andrea De Lorenzo, Marco Virgolin +1
Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains. Tabular Prior-Data Fitted Network (TabPFN), a recent foundation model for…
Rethinking external validation for the target population: Capturing patient-level similarity with a generative model
Mohammad Azizmalayeri, Ameen Abu-Hanna, Saskia Houterman +2
Background: External validation is essential for assessing the transportability of predictive models. However, its interpretation is often confounded by differences between externa…
Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity
Zoë Prins, Samuele Punzo, Frank Wildenburg +2
Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms an…