most citedAlignment Helps Make the Most of Multimodal Data

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026

Invisibilization as a Source of Probability Bias in Language Models

Christian Arnold, Ernesto Calvo, Guadalupe Gonzalez +2

Language models are aligned to avoid using protected attributes such as race, ethnicity, and gender to inform their responses. Therefore, they increasingly refuse or hedge when suc…

cs.CL2024★ 2 cited

Alignment Helps Make the Most of Multimodal Data

Christian Arnold, Andreas Küpfer

Political scientists increasingly analyze multimodal data. However, the effective analysis of such data requires aligning information across different modalities. In our paper, we…