2 papers
cs.CL2025
Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings
Cesar Gonzalez-Gutierrez, Dirk Hovy
Prompting is a common approach for leveraging LMs in zero-shot settings. However, the underlying mechanisms that enable LMs to perform diverse tasks without task-specific supervisi…
cs.CL2025
Domain Pre-training Impact on Representations
Cesar Gonzalez-Gutierrez, Ariadna Quattoni
This empirical study analyzes the effects of the pre-training corpus on the quality of learned transformer representations. We focus on the representation quality induced solely th…