DOVE: Evaluating LLM Cultural Value Alignment Open-Endedly
Discover DOVE, a novel framework for distributional open-ended evaluation of LLMs' cultural value alignment using a value codebook and optimal transport.
Breast Cancer Phenotype Extraction: LLMs vs Ontology Methods
Compare LLMs and classical ontology methods for extracting breast cancer phenotypes from clinical notes to improve oncology data analysis.
Best Demonstration Selection for LLM Next POI Prediction
Explore top demonstration selection methods to boost large language model accuracy in next POI prediction using real-world datasets and heuristics.
How Large Language Models Reflect Human Culture & Behavior
Explore how contemporary large language models reveal key themes of human culture, behavior, and societal norms through AI-driven analysis.
Tool-MCoT: Efficient Multimodal Content Safety Moderation
Discover Tool-MCoT, a tool-augmented multimodal model enhancing content safety moderation with improved accuracy and efficiency for scalable deployment.