BLEU on PlumePHPhttps://plumephp.com/tags/bleu/Recent content in BLEU on PlumePHPHugozh-CNSun, 27 Sep 2026 11:30:00 +0800模型评估与基准：从分类指标到 LLM-as-Judgehttps://plumephp.com/ai-model-evaluation/Sun, 27 Sep 2026 11:30:00 +0800https://plumephp.com/ai-model-evaluation/模型评估：分类回归指标、生成式评估、评测集构建、离线与在线评估、模型卡与持续评估流程。