Evaluator Mapping
【免费下载链接】awesome-copilotCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.项目地址: https://gitcode.com/GitHub_Trending/aw/awesome-copilot
Built-in evaluators used
| Evaluator name | Criterion it covers | Applies to |
|---|---|---|
| Factuality | Factual accuracy | All items |
| ClosedQA | Answer correctness | Items with expected_output |
Agent evaluators
| Evaluator name | Criterion it covers | Applies to | Source file |
|---|---|---|---|
| pixie_qa/evaluators.py:extraction_accuracy | Content accuracy vs source | All items | pixie_qa/evaluators.py |
| pixie_qa/evaluators.py:noise_handling | Navigation/boilerplate noise | All items | pixie_qa/evaluators.py |
Manual custom evaluators (mechanical checks only)
| Evaluator name | Criterion it covers | Applies to | Source file |
|---|---|---|---|
| pixie_qa/evaluators.py:required_fields_present | Required field check | All items | pixie_qa/evaluators.py |
Applicability summary
- Dataset-level defaults(apply to all items): Factuality, pixie_qa/evaluators.py:extraction_accuracy
- Item-specific(apply to subset): ClosedQA (only items with expected_output)
这份清单之所以重要,是因为数据集的求值器作用域有两种:**数据集级默认求值器**(适用于所有条目,来自 Step 1c 中的"通用准则")与**条目级求值器**(仅适用于特定子集,来自"场景专属准则")。在 [testing-api.md](https://link.gitcode.com/i/1a9aa02d7b51855582815e896853e351) 中可见其执行规则:条目省略 `evaluators` 字段则继承数据集默认值;写 `["...", "ClosedQA"]` 表示默认值加 ClosedQA;写 `["OnlyThis"]`(不含 `"..."`)则**只用** OnlyThis、完全不用默认值。 ### 输出清单 - 自定义求值器实现:`pixie_qa/evaluators.py`(如需要自定义求值器) - `pixie_qa/03-evaluator-mapping.md`:准则到求值器的映射 --- ## 5. 与后续步骤的衔接:从定义到验证 ### 5.1 Agent 求值器如何参与 `pixie test` 定义完成后,Step 4 数据集按名字引用求值器,Step 5 用 `pixie test` 运行(参见 [5-run-tests.md](https://link.gitcode.com/i/8efe9af47af685be6a58863acf37c155)): ```bash uv run pixie test uv run pixie test -v # 输出每条用例的分数与求值器 reasoning【免费下载链接】awesome-copilotCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.项目地址: https://gitcode.com/GitHub_Trending/aw/awesome-copilot
创作声明:本文部分内容由AI辅助生成(AIGC),仅供参考