- fix stage-numbering conflict (README vs 05-Progress) and unify stage-1 reading scope - resolve AWS workshop prerequisite contradiction in 04-Reference/01 - convert medium-path wikilinks to vault-root paths (~30 links), fix .pyy typos, annotate ragas fork, unify archive status, add 01-/02- README hubs - compress old-version guidebook notes (01, 05) into pointers; add 2026 reading guidance to 00-Overview - dedupe project templates and remove embedded template copy in 03-Practice/README
53 lines
2.3 KiB
Markdown
53 lines
2.3 KiB
Markdown
---
|
||
type: reference
|
||
tags:
|
||
- llm-evaluation
|
||
- evaluation-infrastructure
|
||
status: active
|
||
created: 2026-08-21
|
||
---
|
||
|
||
# 01 · Evaluation Infrastructure
|
||
|
||
主题:Evaluation Harness、Sandbox、Trace、Scaling
|
||
|
||
## S 级资源(必须认真研究)
|
||
|
||
### 1. UK AISI Engineering Playbook + Inspect AI
|
||
- 仓库:https://github.com/UKGovernmentBEIS/inspect_ai
|
||
- 背景:英国人工智能安全研究所(UK AISI)官方开源
|
||
- 为什么看:国家级安全评测机构测试前沿模型时使用的完整底座
|
||
- 核心思想:把评测基础设施拆成五层
|
||
- Evaluate
|
||
- Isolate
|
||
- Connect
|
||
- Run
|
||
- Scale
|
||
- 重点抽象(映射到自己的体系):
|
||
- Task → Case
|
||
- Dataset → Dataset
|
||
- Solver → Model / Agent Adapter
|
||
- Tool / Sandbox → 隔离执行环境
|
||
- Scorer → Grader
|
||
- Log → Trace / Outcome
|
||
- 适合阶段:完成第一个小项目以后
|
||
|
||
### 2. AWS Generative AI Evaluations Workshop
|
||
- 为什么看:目前垂直场景最全、最硬核的可运行实战代码
|
||
- 覆盖场景:Multimodal RAG / Tool Calling(5 种渐进式评测方法)/ Automated Reasoning(SMT 求解器)/ Multi-Agent Shared Context / Red Teaming(完整介绍与链接见 [[01_Projects/Personal-Tech/LLM_Evaluation/04-Reference/archive/01-Curated-External-Resources|archive/01]])
|
||
- 学习方式(重要):
|
||
不要只照着 Notebook 跑。每个模块都问:
|
||
- Task 是什么?
|
||
- Case 怎么构造?
|
||
- Rubric 是什么?
|
||
- Grader 是什么?
|
||
- Failure 如何定义?
|
||
- 如何做成 Regression?
|
||
- 适合阶段:完成第一个小项目以后(与本节开头一致);精读顺序上建议作为四个 S 级资源中第一个上手(见 [[01_Projects/Personal-Tech/LLM_Evaluation/04-Reference/README|04-Reference 资源地图]])
|
||
|
||
## 次级参考
|
||
- Hugging Face evaluation-guidebook(已在本目录下:[[01_Projects/Personal-Tech/LLM_Evaluation/04-Reference/evaluation-guidebook/00-Overview|evaluation-guidebook]])
|
||
- DeepEval(应用级单元测试框架,上手快但抽象层较浅)
|
||
|
||
> 🔗 本页资源的完整链接、来源背景与上手建议见 [[01_Projects/Personal-Tech/LLM_Evaluation/04-Reference/archive/01-Curated-External-Resources|archive/01-Curated-External-Resources]]("国家级与顶级学术机构"与"云厂商生产环境"两节)。
|