2 Matching Annotations
  1. Last 7 days
  2. huggingface.co huggingface.co
    Reasoning Shift: How Context Silently Shortens LLM Reasoning
    1
    1. fxp007 09 Apr 2026
      the robustness of these reasoning behaviors remains underexplored

      「推理行为的鲁棒性尚未被充分探索」——这句话是整个推理模型研究领域的集体盲点声明。过去两年，测试时计算（test-time compute）、长思维链（CoT）、o1/R1 类推理模型吸引了巨大关注，但几乎所有评测都在「孤立问题」环境下进行。在真实 Agent 部署场景中，「能否保持推理深度」这个最基本的可靠性问题，直到这篇论文才开始被系统研究。

      research-gap robustness test-time-compute systematic-evaluation
    Visit annotations in context

    Tags

    Annotators

    URL

    huggingface.co/papers/2604.01161
  3. Sep 2020
  4. erj.ersjournals.com erj.ersjournals.com
    Systematic evaluation and external validation of 22 prognostic models among hospitalised adults with COVID-19: An observational cohort study
    1
    1. ErikStuchly 28 Sep 2020

      Gupta, R. K., Marks, M., Samuels, T. H. A., Luintel, A., Rampling, T., Chowdhury, H., Quartagno, M., Nair, A., Lipman, M., Abubakar, I., Smeden, M. van, Wong, W. K., Williams, B., & Noursadeghi, M. (2020). Systematic evaluation and external validation of 22 prognostic models among hospitalised adults with COVID-19: An observational cohort study. European Respiratory Journal. https://doi.org/10.1183/13993003.03498-2020

      is:article lang:en COVID-19 evaluation systematic analysis external validity modeling prognosis observational study clinical impact predictor age oxygen saturation
    Visit annotations in context

    Tags

    Annotators

    URL

    erj.ersjournals.com/content/early/2020/09/17/13993003.03498-2020