Tag: benchmark evaluation

Researchers built ResCity-LLM, a pipeline that turns fragmented urban resilience literature into specialized language models whose best adapted version outscored ...

Researchers at Guangdong University of Technology have developed DP-MVAD, a dual-path multi-view framework that disentangles trends from perturbations and fuses ...

Researchers developed EntQA, a reference-free, entity-centric metric that scores how faithfully large language models preserve clinically relevant concepts in medical ...

A new study finds that the locally deployable Gemma 3 27B model scores highly on a German introductory physics benchmark ...

An open-source Windows runtime called OpenTangYuan lets AI language-model agents discover and execute local file, browser, email and tool operations ...

A large-scale study from the University of São Paulo tested three strategies for detecting outliers in categorical and mixed data ...

Researchers at the University of Sassari have developed PSDFS, a feature-selection method that splits each feature into above- and below-mean ...

A new survey maps the full landscape of instruction-based image editing, from GAN origins to diffusion and autoregressive systems, and ...