知识卡片
可验证任务依赖外部标准
验证器适用于能给出明确判定规则的任务,如受限定的数学题或具有测试规范的代码题。它把部分判断责任转移到解析器、参考答案和执行环境,因此工具自身的覆盖范围、错误和资源限制也会影响最终分数。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 评估推理模型
原书出处 · 1 处
- · 查看原书依据
domains that can be easily (and ideally deterministically) verified, such as math and code. Also, this approach can introduce additional complexity and dependencies, and it may shift part of the evaluation burden from the model itself to the external tool.
参考来源
- 位置:《Build a Reasoning Model (From Scratch)》第03章《评估推理模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/chapter-3.html)
- 结论依据:摘录中关于可验证任务依赖外部标准的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:domains that can be easily (and ideally deterministically) verified, such as math and code. Also, this approach can introduce additional complexity and dependencies, and it may shift part of the evaluation burden from the model itself to the external tool.