https://elated-raman-42e0c2.netlify.app/tags/metric/Recent content in Metric on Sawyer Zheng's BlogHugozh-cnSun, 19 Jul 2026 07:21:13 +0800https://elated-raman-42e0c2.netlify.app/post/notes/ai/nlp/llm/eval_metrics/Sun, 04 Jan 2026 00:00:00 +0000https://elated-raman-42e0c2.netlify.app/post/notes/ai/nlp/llm/eval_metrics/<div id="outline-container-headline-1" class="outline-2"> <h2 id="headline-1"> 大模型的输出结果如何评估？ </h2> <div id="outline-text-headline-1" class="outline-text-2"> <p>面对开放型文档结果，如何评估大模型的输出</p> </div> </div> <div id="outline-container-headline-2" class="outline-2"> <h2 id="headline-2"> 指标收集 </h2> <div id="outline-text-headline-2" class="outline-text-2"> <ol> <li> <p>DSPy 中的指标</p> <ul> <li><a href="https://github.com/stanfordnlp/dspy/blob/main/dspy/evaluate/metrics.py">dspy/dspy/evaluate/metrics.py at main · stanfordnlp/dspy · GitHub</a></li> <li><a href="https://github.com/stanfordnlp/dspy/blob/main/dspy/evaluate/auto_evaluation.py">dspy/dspy/evaluate/auto_evaluation.py at main · stanfordnlp/dspy · GitHub</a></li> </ul> </li> <li> <p>G-Eval</p> <ul> <li>基于大模型，生成打分标准，自动打分</li> <li> <p>优势：</p>