领域知识的微调与检索
何时应该微调模型，何时应该使用检索？学习将领域知识注入模型时的权衡、成本和决策框架。
领域知识的微调与检索 是 CoddyKit 上的免费 Prompt Engineering & LLM Optimization for Developers 课时。 这是第 4 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 Prompt Engineering & LLM Optimization for Developers 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Prompt Engineering & LLM Optimization for Developers 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
Two Ways to Specialize
To make an LLM expert in your domain you can:
- Fine-tune: adjust the model weights on your data
- Retrieve: fetch relevant documents at query time (RAG)
Often the best answer is a combination of both.
What Fine-Tuning Changes
Fine-tuning bakes patterns into the weights. It is excellent for teaching style, format, and behavior — for example always replying in a strict JSON shape or a brand voice.
What Retrieval Changes
Retrieval injects facts at runtime without touching weights. It shines when knowledge is large, frequently updated, or must be cited to a source.
Freshness Matters
A fine-tuned model freezes knowledge at training time. If your facts change daily (prices, policies, inventory), retrieval wins because you just update the document store.
Cost Comparison
Fine-tuning has upfront training cost and a new model to maintain. Retrieval has ongoing per-query embedding and storage cost but no retraining. Match the model to your update cadence.
A Fine-Tuning Example
Fine-tuning data is usually prompt/response pairs in JSONL. The model learns to imitate the desired responses.
{"messages":[{"role":"user","content":"Summarize ticket 42"},{"role":"assistant","content":"Priority: high. Issue: login fails."}]}A Retrieval Example
RAG embeds the query, finds nearby chunks, and stuffs them into the prompt as context.
const docs = vectorStore.search(embed(query), 5);
const prompt = buildPrompt(query, docs);
const answer = await llm(prompt);Hallucination Risk
Fine-tuning on facts can increase hallucination — the model confidently states learned facts even when wrong. Retrieval lets you cite and verify, reducing fabrication.
Combining Both
A powerful pattern: fine-tune for behavior and format, use retrieval for current facts. The model knows how to act; the documents tell it what is true today.
Data Requirements
Fine-tuning needs hundreds to thousands of clean, consistent examples. Retrieval needs only well-chunked documents and embeddings — far less labeling effort to start.
A Decision Checklist
Choose retrieval if knowledge is large, changing, or must be cited. Choose fine-tuning if you need consistent style/format or lower per-call latency on a fixed behavior. Combine them when you need both.
Quick Check
Test your understanding.
Recap
You compared fine-tuning (best for style, format, behavior) with retrieval (best for large, fresh, citable facts). Fine-tuning can worsen factual hallucination; combining a fine-tuned behavior model with retrieval for facts is often the strongest domain customization.
常见问题解答
「领域知识的微调与检索」课时是免费的吗？
是的 — 「领域知识的微调与检索」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Prompt Engineering & LLM Optimization for Developers 课程的其余内容，请升级到 CoddyKit PRO。 Prompt Engineering & LLM Optimization for Developers 课程共包含 4 节课。
「领域知识的微调与检索」这节课中我会学到什么？
何时应该微调模型，何时应该使用检索？学习将领域知识注入模型时的权衡、成本和决策框架。 你通过在浏览器中直接运行的动手代码来练习 Prompt Engineering & LLM Optimization for Developers，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 Prompt Engineering & LLM Optimization for Developers 需要有经验吗？
无需任何先前经验。CoddyKit 上的 Prompt Engineering & LLM Optimization for Developers 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 4 节课，共 4 节。
「领域知识的微调与检索」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 Prompt Engineering & LLM Optimization for Developers 课中编写并运行代码吗？
能。每节 Prompt Engineering & LLM Optimization for Developers 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。
此课程中的所有课时
- 特定领域的提示策略
- 集成知识图谱
- 混合 LLM 方法（符号方法 + 神经方法）
- 领域知识的微调与检索