From 9c88db6d0f27c37e22d18b884955f4c01a4ab027 Mon Sep 17 00:00:00 2001 From: windyboy Date: Wed, 26 Aug 2026 17:13:57 +0800 Subject: [PATCH] refactor: rename template files to English and update file paths in docs --- .../02-First-Week-Worksheet.md | 18 ++-- .../01-go-docs-qa/00-project-overview.md | 4 +- .../01-go-docs-qa/01-task-and-rubric.md | 2 + .../01-go-docs-qa/02-case-design.md | 96 +++++++++++++++++++ .../LLM_Evaluation/03-Practice/README.md | 28 +++--- ...{00-项目概览.md => 00-project-overview.md} | 1 + ...-任务与Rubric.md => 01-task-and-rubric.md} | 2 + .../{02-Case设计.md => 02-case-design.md} | 14 +++ ...行与盲评.md => 03-run-and-blind-review.md} | 2 + .../{04-失败复盘.md => 04-failure-review.md} | 0 ...与回归.md => 05-change-and-regression.md} | 0 .../05-Progress/02-方法季度复盘.md | 2 +- 12 files changed, 145 insertions(+), 24 deletions(-) create mode 100644 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/02-case-design.md rename 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/{00-项目概览.md => 00-project-overview.md} (92%) rename 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/{01-任务与Rubric.md => 01-task-and-rubric.md} (90%) rename 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/{02-Case设计.md => 02-case-design.md} (69%) rename 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/{03-运行与盲评.md => 03-run-and-blind-review.md} (94%) rename 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/{04-失败复盘.md => 04-failure-review.md} (100%) rename 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/{05-变更与回归.md => 05-change-and-regression.md} (100%) diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/02-Practical-Roadmap/02-First-Week-Worksheet.md b/01_Projects/Personal-Tech/LLM_Evaluation/02-Practical-Roadmap/02-First-Week-Worksheet.md index fd5c7bb..a81533a 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/02-Practical-Roadmap/02-First-Week-Worksheet.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/02-Practical-Roadmap/02-First-Week-Worksheet.md @@ -13,22 +13,22 @@ created: 2026-08-21 **使用方法:** 不要先研究工具。直接复制本文件,为一个公开文档问答小任务填写空白处。只要完成到“10 个 case + rubric + 一次盲评”,就已经完成了真正的第一步。 -> **填完放哪:** 填写完成的副本**复制进 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README|03-Practice]] 下你的项目目录**(骨架见 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览|03-Practice/_template/]]),本文件只保留空白模板,供以后复用。 +> **填完放哪:** 填写完成的副本**复制进 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README|03-Practice]] 下你的项目目录**(骨架见 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview|03-Practice/_template/]]),本文件只保留空白模板,供以后复用。 > **与路线图的关系:** 本工作表是《LLM 评测工程实战路线图》Day 1—3 的填空版,按“首周最低 10 个 case”设计;若时间充裕,可按路线图扩展至 20 个。 ### 填写内容 → 项目文件的对应关系 -工作表填完后,把内容按下面的对应关系整理进项目目录(骨架见 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览|03-Practice/_template/]]): +工作表填完后,把内容按下面的对应关系整理进项目目录(骨架见 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview|03-Practice/_template/]]): | 工作表小节 | 对应项目文件 | |---|---| -| 第 0 节:任务边界 | `00-项目概览.md`(问题/成功条件/风险)+ `01-任务与Rubric.md`(任务边界表) | -| 第 1 节:Rubric v0.1 | `01-任务与Rubric.md` | -| 第 2 节:10 个 case | `02-Case设计.md` | -| 第 3-4 节:候选与盲评 | `03-运行与盲评.md` | -| 第 5 节:失败分类 | `04-失败复盘.md` | -| 第 6 节:修改与回归 | `05-变更与回归.md` | +| 第 0 节:任务边界 | `00-project-overview.md`(问题/成功条件/风险)+ `01-task-and-rubric.md`(任务边界表) | +| 第 1 节:Rubric v0.1 | `01-task-and-rubric.md` | +| 第 2 节:10 个 case | `02-case-design.md` | +| 第 3-4 节:候选与盲评 | `03-run-and-blind-review.md` | +| 第 5 节:失败分类 | `04-failure-review.md` | +| 第 6 节:修改与回归 | `05-change-and-regression.md` | > 也就是说:工作表 = 第一次闭环的线性填空;项目目录 = 长期项目的分文件结构。填完工作表后把内容迁移进项目目录,就进入长期迭代(对应学习看板 Level 2 → Level 3)。 @@ -46,6 +46,8 @@ created: 2026-08-21 | 非目标 | 例如:不评价文档外的常识正确性 | | 数据来源 / 许可 | 例如:Python 官方文档某页面,记录 URL 与日期 | +- [ ] 已把输入上下文原文(文档片段/工具定义)粘贴并冻结(含抓取日期),放入项目 `02-case-design.md` 顶部"输入上下文(冻结快照)"小节 + ### 停下来检查 如果你仍写的是“回答要专业”或“Agent 要聪明”,说明范围还不够小。把它改成一个可观察行为:引用、拒答、工具参数、权限、状态变化或可执行性。 diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/00-project-overview.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/00-project-overview.md index 101ad1f..ac51df2 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/00-project-overview.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/00-project-overview.md @@ -31,6 +31,7 @@ created: 2026-08-24 - 来源:Go 官方文档 Module release and versioning workflow / URL:https://go.dev/doc/modules/release-workflow / 日期:2026-08-24 - 许可:Go 文档(BSD 风格)/ PII 政策:N/A(公开技术文档,无个人数据) +- 输入上下文正文:冻结于 `02-case-design.md` 顶部"输入上下文(冻结快照)"小节 ## 主要风险 @@ -49,7 +50,8 @@ created: 2026-08-24 ## 下一步最小动作 -- [ ] 填写 `01-task-and-rubric.md` 的 rubric 三维度(对应 [[02-First-Week-Worksheet]] 第 1 节) +- [x] 填写 `01-task-and-rubric.md` 的 rubric 三维度(对应 [[02-First-Week-Worksheet]] 第 1 节) +- [ ] 对着 `02-case-design.md` 顶部"输入上下文(冻结快照)"填写 10 个 case --- diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/01-task-and-rubric.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/01-task-and-rubric.md index b6b3a3c..6920935 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/01-task-and-rubric.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/01-task-and-rubric.md @@ -19,6 +19,8 @@ status: active | 非目标 | 不评价文档外的 Go 常识(semver、/v2 后缀、go get 细节等) | | 数据来源 / 许可 | 来源 Go 官方文档 release-workflow 页;URL https://go.dev/doc/modules/release-workflow;日期 2026-08-24;BSD 风格;PII:N/A | +> 输入上下文原文(文档片段等)冻结于 `02-case-design.md` 顶部快照;本表只记录出处与许可,不复制原文。 + ## Rubric v0.1(对应工作表第 1 节) | 维度 | 通过条件 | 失败条件 | 正例 | 反例 | diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/02-case-design.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/02-case-design.md new file mode 100644 index 0000000..e783a18 --- /dev/null +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/02-case-design.md @@ -0,0 +1,96 @@ +--- +type: project +status: active +--- + +# 02 · Case 设计 + +> 权威分布表:20-case 配比见 [[01-LLM-Evaluation-Roadmap]] Day 1;10-case 结构见 [[02-First-Week-Worksheet]] 第 2 节。第一版 10-20 个即可。 + +## 输入上下文(冻结快照) + +> 每个 case 的输入 = question + context。context 就是下面这段原文。判"文档能否完整回答"、盲评判"有据性"都以它为界。建数据集时,这段原文原样搬入每个 case 的 `input.context`。 + +- 来源:Go 官方文档 "Module release and versioning workflow"(Common workflow steps 一节)/ URL:https://go.dev/doc/modules/release-workflow / 抓取日期:2026-08-26 +- 许可:Go 文档(BSD 风格)/ PII:N/A(公开技术文档,无个人数据) +- 边界说明:本片段仅含该页 "Common workflow steps" 一节;凡片段未覆盖内容(预发布版本号格式、发布命令/打 tag 操作、v1 稳定性承诺细节、major 版本 /v2 步骤等)一律视为"资料不足"。 + +### 原文(Common workflow steps) + +The following sequence illustrates release and versioning workflow steps for an example new module. For more about each step, see the sections in this topic. + +- **Begin a module and organize its sources** to make it easier for developers to use and for you to maintain. + + If you're brand new to developing modules, check out Tutorial: Create a Go module. + + In Go's decentralized module publishing system, how you organize your code matters. For more, see Managing module source. + +- **Set up to write local client code that calls functions in the unpublished module.** + + Before you publish a module, it's unavailable for the typical dependency management workflow using commands such as `go get`. A good way to test your module code at this stage is to try it while it is in a directory local to your calling code. + + See Coding against an unpublished module for more about local development. + +- **When the module's code is ready for other developers to try it out, begin publishing v0 pre-releases such as alphas and betas.** See Publishing pre-release versions for more. + +- **Release a v0 that's not guaranteed to be stable, but which users can try out.** For more, see Publishing the first (unstable) version. + +- **After your v0 version is published, you can (and should!) continue to release new versions of it.** + + These new versions might include bug fixes (patch releases), additions to the module's public API (minor releases), and even breaking changes. Because a v0 release makes no guarantees of stability or backward compatibility, you can make breaking changes in its versions. + + For more, see Publishing bug fixes and Publishing non-breaking API changes. + +- **When you're getting a stable version ready for release, you publish pre-releases as alphas and betas.** For more, see Publishing pre-release versions. + +- **Release a v1 as the first stable release.** + + This is the first release that makes commitments about the module's stability. For more, see Publishing the first stable version. + +- **In the v1 version, continue to fix bugs and, where necessary, make additions to the module's public API.** + + For more, see Publishing bug fixes and Publishing non-breaking API changes. + +- **When it can't be avoided, publish breaking changes in a new major version.** + + A major version update – such as from v1.x.x to v2.x.x – can be a very disruptive upgrade for your module's users. It should be a last resort. For more, see Publishing breaking API changes. + +## Case 列表(对应工作表第 2 节) + +| 编号 | 类别 | 问题 | 文档能否完整回答 | 预期系统行为 | case 状态 | +| --- | ---: | --- | -------- | ------ | --------- | +| 01 | 正常路径 | | 是 | | candidate | +| 02 | 正常路径 | | 是 | | | +| 03 | 正常路径 | | 是 | | | +| 04 | 资料不足 | | 否 | | | +| 05 | 资料不足 | | 否 | | | +| 06 | 部分支持 | | 部分 | | | +| 07 | 多证据 | | 是 | | | +| 08 | 幻觉诱发 | | 否 / 部分 | | | +| 09 | 格式约束 | | 是 | | | +| 10 | 边界条件 | | 视情况 | | | + +> case 状态流转:candidate → reviewed → accepted → regression → deprecated(定义见 [[01-LLM-Evaluation-Roadmap]] 第五节)。 +> +> 资料不足的写法:不要写完全无关的问题,写"只差一小块信息就能回答"的问题(如文档讲了字段但没有默认值),才能测出模型会不会补全空白。 + +## JSONL 结构(稳定测试定义) + +> 字段与示例见 [[01-LLM-Evaluation-Roadmap]] 第五节。每个 case 至少包含:id / input / expected / metadata(category、difficulty、risk、split、case_status)/ rubric_version / dataset_version。**测试定义与运行记录分开保存**。 +> +> 注意:`input.context` = 顶部"输入上下文(冻结快照)"的原文;运行记录不复制全文,只存 case_id + 版本号(见 [[01-LLM-Evaluation-Roadmap]] 第五节)。 + +```json +{ + "id": "rag-0001", + "input": { "question": "", "context": [] }, + "expected": { "behavior": "", "must_include": [], "must_not_include": [] }, + "metadata": { "category": "", "difficulty": "", "risk": "", "split": "dev", "case_status": "candidate" }, + "rubric_version": "0.1", + "dataset_version": "0.1" +} +``` + +--- + +返回 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README|项目实践入口]]。 diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README.md index 31e532b..c1029e7 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/README.md @@ -15,7 +15,7 @@ created: 2026-08-21 | 项目 | 状态 | 代码仓库 | 最近更新 | 一句话 | |---|---|---|---|---| -| (暂无——从 [[02-First-Week-Worksheet|首周工作表]] 开始,复制 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览|`_template/`]] 建立第一个项目) | | | | | +| [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/01-go-docs-qa/00-project-overview\|01-go-docs-qa]] | 进行中(10 个 case 设计) | TBD | 2026-08-26 | Go 官方文档约束下的技术问答(公开文档 RAG 评测) | ## 建议的第一批项目 @@ -25,19 +25,19 @@ created: 2026-08-21 2. `agent-tool-eval/` — 模拟工具调用、权限与状态 3. `code-agent-eval/` — 编译、测试、静态分析与回归 -> 每个项目复制 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览|`_template/` 骨架]](6 个文件)即可开始;骨架内的引导说明引用了工作表与路线图,不重复内容。 +> 每个项目复制 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview|`_template/` 骨架]](6 个文件)即可开始;骨架内的引导说明引用了工作表与路线图,不重复内容。 每个项目创建独立子目录,例如: ```text 03-Practice/ └── 2026-我的第一个公开文档问答评测/ - ├── 00-项目概览.md - ├── 01-任务与Rubric.md - ├── 02-Case设计.md - ├── 03-运行与盲评.md - ├── 04-失败复盘.md - └── 05-变更与回归.md + ├── 00-project-overview.md + ├── 01-task-and-rubric.md + ├── 02-case-design.md + ├── 03-run-and-blind-review.md + ├── 04-failure-review.md + └── 05-change-and-regression.md ``` 每个项目至少保留: @@ -57,11 +57,11 @@ reports/ | 工作表 / 模板(Obsidian 项目目录) | 代码仓库目录(路线图 §4 的 `llm-eval-lab/` 结构) | |---|---| -| `00-项目概览.md` + `01-任务与Rubric.md` | `task.md` + `rubrics/` | -| `02-Case设计.md` | `datasets/`(冻结的 eval 定义,JSONL) | -| `03-运行与盲评.md` | `runs/`(原始输出 + 盲评记录) | -| `04-失败复盘.md` | `reports/`(确认的失败入 `datasets/regression/`) | -| `05-变更与回归.md` | `scripts/`(validate / eval)+ CI 配置 | +| `00-project-overview.md` + `01-task-and-rubric.md` | `task.md` + `rubrics/` | +| `02-case-design.md` | `datasets/`(冻结的 eval 定义,JSONL) | +| `03-run-and-blind-review.md` | `runs/`(原始输出 + 盲评记录) | +| `04-failure-review.md` | `reports/`(确认的失败入 `datasets/regression/`) | +| `05-change-and-regression.md` | `scripts/`(validate / eval)+ CI 配置 | ## 为什么笔记和数据要分开 @@ -86,7 +86,7 @@ reports/ ## 项目模板 -新项目的 `00-项目概览.md` 直接复制 `_template/00-项目概览.md`(骨架见 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览|`_template/`]]);本页不再内嵌模板副本,避免与模板文件漂移。 +新项目的 `00-project-overview.md` 直接复制 `_template/00-project-overview.md`(骨架见 [[01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview|`_template/`]]);本页不再内嵌模板副本,避免与模板文件漂移。 ## 开始前 diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview.md similarity index 92% rename from 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览.md rename to 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview.md index 355c41c..e6e99af 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-项目概览.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/00-project-overview.md @@ -33,6 +33,7 @@ created: 2026-08-21 - 来源:/ URL:/ 日期: - 许可:/ PII 政策: +- 输入上下文正文:冻结于 `02-case-design.md` 顶部"输入上下文(冻结快照)"小节 ## 主要风险 diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/01-任务与Rubric.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/01-task-and-rubric.md similarity index 90% rename from 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/01-任务与Rubric.md rename to 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/01-task-and-rubric.md index a6b4180..7f1180b 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/01-任务与Rubric.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/01-task-and-rubric.md @@ -19,6 +19,8 @@ status: active | 非目标 | | | 数据来源 / 许可 | | +> 输入上下文原文(文档片段等)冻结于 `02-case-design.md` 顶部快照;本表只记录出处与许可,不复制原文。 + ## Rubric v0.1(对应工作表第 1 节) | 维度 | 通过条件 | 失败条件 | 正例 | 反例 | diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/02-Case设计.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/02-case-design.md similarity index 69% rename from 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/02-Case设计.md rename to 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/02-case-design.md index e5094a7..45060ae 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/02-Case设计.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/02-case-design.md @@ -7,6 +7,18 @@ status: active > 权威分布表:20-case 配比见 [[01-LLM-Evaluation-Roadmap]] Day 1;10-case 结构见 [[02-First-Week-Worksheet]] 第 2 节。第一版 10-20 个即可。 +## 输入上下文(冻结快照) + +> 每个 case 的输入 = question + context。context 就是下面这段原文(文档片段 / 工具定义 / 代码片段)。判"文档能否完整回答"、盲评判"有据性"都以它为界。建数据集时,这段原文原样搬入每个 case 的 `input.context`。 + +- 来源:____(URL)/ 抓取日期:____ +- 许可:____ / PII:____ +- 边界说明:____(例如:本片段仅含文档的 X 节,凡未覆盖内容一律视为"资料不足") + +### 原文(粘贴处) + +<粘贴输入上下文原文,保留原始措辞与格式> + ## Case 列表(对应工作表第 2 节) | 编号 | 类别 | 问题 | 文档能否完整回答 | 预期系统行为 | case 状态 | @@ -29,6 +41,8 @@ status: active ## JSONL 结构(稳定测试定义) > 字段与示例见 [[01-LLM-Evaluation-Roadmap]] 第五节。每个 case 至少包含:id / input / expected / metadata(category、difficulty、risk、split、case_status)/ rubric_version / dataset_version。**测试定义与运行记录分开保存**。 +> +> 注意:`input.context` = 顶部"输入上下文(冻结快照)"的原文;运行记录不复制全文,只存 case_id + 版本号(见 [[01-LLM-Evaluation-Roadmap]] 第五节)。 ```json { diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/03-运行与盲评.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/03-run-and-blind-review.md similarity index 94% rename from 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/03-运行与盲评.md rename to 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/03-run-and-blind-review.md index 9ec019d..b98000d 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/03-运行与盲评.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/03-run-and-blind-review.md @@ -21,6 +21,8 @@ status: active ## 盲评记录(对应工作表第 4 节) +> 判"有据性"与"资料不足"时,对照 `02-case-design.md` 顶部"输入上下文(冻结快照)"。 + | Case | A:有据性 | A:资料不足 | A:完成度 | B:有据性 | B:资料不足 | B:完成度 | 更优/平局 | 一句话理由 | 置信度 | |---|---|---|---|---|---|---|---|---|---| | 01 | | | | | | | | | | high/low | diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/04-失败复盘.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/04-failure-review.md similarity index 100% rename from 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/04-失败复盘.md rename to 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/04-failure-review.md diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/05-变更与回归.md b/01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/05-change-and-regression.md similarity index 100% rename from 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/05-变更与回归.md rename to 01_Projects/Personal-Tech/LLM_Evaluation/03-Practice/_template/05-change-and-regression.md diff --git a/01_Projects/Personal-Tech/LLM_Evaluation/05-Progress/02-方法季度复盘.md b/01_Projects/Personal-Tech/LLM_Evaluation/05-Progress/02-方法季度复盘.md index 7074b4d..05648a1 100644 --- a/01_Projects/Personal-Tech/LLM_Evaluation/05-Progress/02-方法季度复盘.md +++ b/01_Projects/Personal-Tech/LLM_Evaluation/05-Progress/02-方法季度复盘.md @@ -10,7 +10,7 @@ created: 2026-08-21 # 方法季度复盘(含作品集清单) -> **使用方式:** 每季度一次(约第 12 周)。复盘对象是**这套学习方法本身**,不是单个项目(单个项目的复盘在 `03-Practice/项目名/04-失败复盘.md`)。 +> **使用方式:** 每季度一次(约第 12 周)。复盘对象是**这套学习方法本身**,不是单个项目(单个项目的复盘在 `03-Practice/项目名/04-failure-review.md`)。 ## 方法论自评