PulseAugur / Brief
EN
LIVE 19:48:32

Brief

last 24h
[2/2] 224 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. RESEARCH · arXiv cs.LG English(EN) · · [2 sources]

    Zero-Shot Active Feature Acquisition via LLM-Elicitation

    Researchers have developed a novel framework for zero-shot active feature acquisition (AFA) by leveraging large language models (LLMs) through a disciplined elicitation process. This method focuses on extracting specific statistical information from LLMs, such as unary deviations and pairwise co-variations, which are then used to guide feature selection for classification or ranking tasks. The framework was evaluated on a cohort of Inflammatory Bowel Disease (IBD) patients, demonstrating superior performance compared to existing methods, particularly for complex cases. AI

    Zero-Shot Active Feature Acquisition via LLM-Elicitation

    IMPACT This research could improve diagnostic accuracy and efficiency in healthcare by enabling more effective feature selection in complex patient cases.

  2. RESEARCH · arXiv cs.LG English(EN) · · [2 sources]

    Donor-Aware scRNA-seq Benchmarks for IBD Classification

    Researchers have developed a donor-aware benchmark for classifying Inflammatory Bowel Disease (IBD) using single-cell RNA sequencing (scRNA-seq) data. This new benchmark addresses the issue of pseudoreplication by ensuring that training and testing data come from different donors. The study evaluated three feature representations, including centered log-ratio (CLR) transformed cell-type composition and GatedStructuralCFN dependency embeddings, across two independent IBD cohorts. AI

    Donor-Aware scRNA-seq Benchmarks for IBD Classification

    IMPACT Introduces a more rigorous evaluation framework for biological data analysis, potentially improving the reliability of AI models in disease classification.