🏢 University of Copenhagen

GFS-VL: Enhancing few-shot 3D segmentation by synergizing vision-language models with few-shot learning for robust real-world application.

LLMs struggle with positional bias and lack transparency when summarizing long contexts. This paper introduces SUnsET dataset and fine-tuning methods to improve unstructured evidence citation and summ…

Community moderation success relies on fact-checking!

LLMs personalize based on user names, but this study reveals that cultural presumptions in LLM responses risk reinforcing stereotypes.

Fact-checkers need explainable AI: This study reveals how AI tools can better support fact-checkers by providing explanations tailored to their workflows, addressing unmet needs, and improving the eff…