Files
my-vault/01_Projects/Personal-Tech/LLM_Evaluation/04-Reference/README.md
T
windyboy 63add96a09 dedupe LLM_Evaluation zone: single-source tables, fix nav orphans, compress guidebook 2025
- Why Guide: remove duplicated 20-case/rubric/test-definition tables, link to
  authoritative Roadmap/Worksheet instead; 10-min action points to entries
- Concept Map / What-Is: cross-link narrative vs quick-reference roles
- Worksheet: annotate sections with authoritative sources
- 04-Reference 01-04 <-> archive/01: bidirectional resource links
- archive/00-Material-List: shrink guidebook listing, now reachable from READMEs
- guidebook: compress 06-Yearly-Dives 2025 section (-> 08-2025-Edition §3),
  add old/new version nav banners to 01-05, reverse links in 08
- README/Start-Here: link Learning Board (was orphaned)
2026-08-21 17:25:12 +08:00

2.6 KiB
Raw Blame History

type, tags, status, created
type tags status created
moc
llm-evaluation
learning-zone
moc
active 2026-08-21

04-Reference · LLM Evaluation 资源地图

本目录不是"收藏夹",而是评测工程能力地图
每个资源都对应明确的能力点,并标明「为什么看、什么时候看、重点看什么」。

五层能力框架

1. Evaluation Methodology
   ↓
2. Benchmark & Reproducibility
   ↓
3. System / Agent Evaluation
   ↓
4. Continuous Evaluation / CI
   ↓
5. Safety / Sandbox / Environment

对应到本仓库:

00-Foundations          ← 方法论基础
01-Getting-Started      ← 为什么做评测
02-Practical-Roadmap    ← 工程路线
03-Practice             ← 自己动手的 Lab
04-Reference            ← 本目录(深度参考)

推荐学习顺序(只精读 4 个)

  1. AWS Generative AI Evaluations Workshop
    → 先看实际 Eval 长什么样(RAG / Tool Calling / Multi-Agent / Red Teaming

  2. EleutherAI lm-evaluation-harness
    → 理解标准化 Task、Prompt 固定、Metric 配置、去污染机制

  3. Inspect AI + AISI Engineering Playbook
    → 现代 Evaluation Framework 的抽象(Task / Solver / Scorer / Sandbox / Trace

  4. Ai2 OLMES / olmo-eval
    → 如何把 Evaluation Protocol 真正冻结,实现可复现比较

后续按需:

  • CircleCI + RAGAS → Continuous Evaluation
  • BenchFlow → Environment-based Agent Evaluation

文件索引

文件 对应能力 核心资源
01-Evaluation-Infrastructure Harness / Sandbox / Scaling Inspect AI, AISI Playbook, AWS Workshop
02-Benchmark-and-Reproducibility 标准化 / 去污染 / 可复现 lm-evaluation-harness, OLMES
03-Continuous-Evaluation CI Gate / Experiment Tracking RAGAS + CircleCI, W&B
04-Agent-Safety-and-Environments Tool Use / Sandbox / Trajectory Inspect Sandbox, BenchFlow
05-Source-Reading-Checklist 统一阅读方法论 固定的 8 个问题
04-Reference/evaluation-guidebook/00-Overview 方法论补充 Hugging Face 官方 Guidebook
04-Reference/archive/00-Material-List 早期草案与外部资源归档 索引见 00-Material-List

原则

  • 优先官方 docs、源码、Design Doc
  • 二手博客 / 课程宣传只做导航,不作为主线
  • 每读一个框架,强制用 05-Source-Reading-Checklist 的 8 个问题对照