---
title: "什么是 LLM (Large Language Model)？"
canonical: https://wavect.io/zh/glossary/llm/
language: zh
description: "一种经过训练以预测下一个 token 的统计模型，这使它在语言任务上出奇地出色，而在任何需要保证正确性的事情上都不可靠。"
image: "https://wavect.io/img/general/bak/open_graph_preview.jpg"
---

技术

# LLM

Large Language Model

一种经过训练以预测下一个 token 的统计模型，这使它在语言任务上出奇地出色，而在任何需要保证正确性的事情上都不可靠。

最近审阅: 2026-06-02 审阅人 [Kevin Riedl](/zh/team/kevin-riedl/) [wiki ↗](https://www.wikidata.org/wiki/Q139796365)

LLM 是一种在海量文本上训练、只做一件事的模型：根据之前的全部内容预测下一个 token（大致是下一个词片段）。把足够多的这种预测叠加起来，就得到了流畅的回答、摘要、翻译和代码。这就是全部的诀窍。它不是人类意义上的推理，而是非常出色的模式补全。

这一点很重要，因为它同时解释了魔力与局限。LLM 对你的业务没有记忆，没有超出其训练截止日期的知识，也没有内置的保证它给出的流畅回答是真实的。它会用与正确事实完全相同的自信说出一个错误事实。这种失败有个名字，叫 [幻觉](/zh/glossary/hallucination/) ，它不是一个可以打补丁修掉的故障，而是下一个 token 预测在缺乏接地时必然产生的结果。把它当作工具，而不是神谕。

正确的架构，举个实际例子：一家公司想要一个能回答自家合同问题的助手。朴素的做法是直接问原始模型，结果得到自信而错误的引用。能跑通的做法是把模型包裹起来：用 [RAG](/zh/glossary/rag/) 在查询时检索相关的合同条款，让答案来自公司自己的文档而不是模型训练时刻的知识，输出对照一个 schema 做校验，任何触发法律动作的请求都经由人工。模型没有变聪明；是它周围的工程变得认真了。

创始人最常犯的错误，是用一个更大的模型去修一个接地问题，或者在真正需要检索时去做 [微调](/zh/glossary/fine-tuning/) 。微调改变的是风格和格式；它不能可靠地注入事实，而且你的数据一变它就过时。诚实的取舍：当你需要确定性的、可审计的输出时，LLM 就是错误的工具，税务计算、监管逻辑，任何「通常正确」就构成隐患的场景；而它正适合起草、分类、抽取，以及在你自己的数据上做搜索。放进一个 [Agent 式](/zh/glossary/ai-agents/) 循环里，它就能行动，而不只是回答，这又把赌注抬高了一层。我们在 [人工智能](/zh/services/artificial-intelligence/) 下构建的正是这种有接地、经校验的系统。当作真理来源使用时，LLM 是一个充满自信的隐患。

// FAQ

## 常见问题

### 用简单的话说，什么是 LLM？

一种根据已有文本预测下一段文本的模型。在足够的数据上训练后，这种预测会产生流畅、有用的回答。它是大规模的模式补全，而不是理解。

### 什么时候 LLM 是错误的工具？

当你需要保证正确且可审计的答案时。LLM 是概率性的，所以对于税务计算、合规逻辑，或任何自信的错误答案会带来危险的场景，应使用确定性代码，让 LLM 只在边缘处辅助。

### LLM 知道当前事件吗？

只知道到其训练截止日期为止的内容。任何更新的内容，或任何与你业务相关的具体内容，除非你在运行时通过检索把上下文喂给它，否则它都不知道。

相关术语

- [AI Agents](/zh/glossary/ai-agents/)
- [RAG](/zh/glossary/rag/)
- [MCP](/zh/glossary/mcp/)
- [Fine-Tuning](/zh/glossary/fine-tuning/)
- [Hallucination](/zh/glossary/hallucination/)

相关服务

- [人工智能](/zh/services/artificial-intelligence/)

相关案例研究

- [Hyperstate AI](/zh/case-studies/hyperstate-ai/)
- [Twinsoft AI](/zh/case-studies/twinsoft-ai/)

相关指南

- [如何为 MVP 选择技术栈](/zh/software-development-guide/how-to-choose-a-tech-stack-for-mvp/)

聊聊

## Structured Data

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@id": "https://wavect.io/#organization",
      "@type": [
        "Organization",
        "ProfessionalService",
        "LocalBusiness"
      ],
      "employee": [
        {
          "@id": "https://wavect.io/team/kevin-riedl/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Kevin Riedl",
          "url": "https://wavect.io/team/kevin-riedl/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        },
        {
          "@id": "https://wavect.io/team/christof-jori/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Christof Jori",
          "url": "https://wavect.io/team/christof-jori/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        }
      ],
      "founder": [
        {
          "@id": "https://wavect.io/team/kevin-riedl/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Kevin Riedl",
          "url": "https://wavect.io/team/kevin-riedl/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        },
        {
          "@id": "https://wavect.io/team/christof-jori/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Christof Jori",
          "url": "https://wavect.io/team/christof-jori/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        }
      ],
      "legalRepresentative": [
        {
          "@id": "https://wavect.io/team/kevin-riedl/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Kevin Riedl",
          "url": "https://wavect.io/team/kevin-riedl/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        },
        {
          "@id": "https://wavect.io/team/christof-jori/#person",
          "@type": "Person",
          "jobTitle": "Managing Director",
          "name": "Christof Jori",
          "url": "https://wavect.io/team/christof-jori/",
          "worksFor": {
            "@id": "https://wavect.io/#organization",
            "@type": [
              "Organization",
              "ProfessionalService",
              "LocalBusiness"
            ]
          }
        }
      ],
      "name": "Wavect GmbH",
      "subjectOf": {
        "@id": "https://wavect.io/verified-claims.json#dataset",
        "@type": "Dataset",
        "creator": {
          "@id": "https://wavect.io/#organization",
          "@type": [
            "Organization",
            "ProfessionalService",
            "LocalBusiness"
          ]
        },
        "description": "A machine-readable registry of quantitative and qualitative claims published by Wavect, with review dates, localized page appearances and public third-party citations where available.",
        "inLanguage": "en",
        "isAccessibleForFree": true,
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Wavect verified publication claims",
        "url": "https://wavect.io/verified-claims.json"
      },
      "url": "https://wavect.io/"
    },
    {
      "@id": "https://wavect.io/team/kevin-riedl/#person",
      "@type": "Person",
      "jobTitle": "Managing Director",
      "name": "Kevin Riedl",
      "sameAs": [
        "https://www.wikidata.org/wiki/Q139796365",
        "https://www.linkedin.com/in/wsdt",
        "https://github.com/wsdt"
      ],
      "url": "https://wavect.io/team/kevin-riedl/",
      "worksFor": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      }
    },
    {
      "@id": "https://wavect.io/team/christof-jori/#person",
      "@type": "Person",
      "jobTitle": "Managing Director",
      "name": "Christof Jori",
      "sameAs": [
        "https://www.wikidata.org/wiki/Q139796367",
        "https://www.linkedin.com/in/jocr77/",
        "https://github.com/jo-chris"
      ],
      "url": "https://wavect.io/team/christof-jori/",
      "worksFor": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      }
    },
    {
      "@id": "https://wavect.io/#website",
      "@type": "WebSite",
      "inLanguage": [
        "en",
        "de",
        "es",
        "zh"
      ],
      "name": "Wavect",
      "potentialAction": {
        "@type": "SearchAction",
        "query-input": "required name=search_term_string",
        "target": {
          "@type": "EntryPoint",
          "urlTemplate": "https://wavect.io/search/?q={search_term_string}"
        }
      },
      "publisher": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      },
      "url": "https://wavect.io/"
    }
  ]
}
```

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@id": "https://wavect.io/zh/glossary/llm/#term",
      "@type": "DefinedTerm",
      "alternateName": [],
      "description": "一种经过训练以预测下一个 token 的统计模型，这使它在语言任务上出奇地出色，而在任何需要保证正确性的事情上都不可靠。",
      "inDefinedTermSet": "https://wavect.io/zh/glossary/#termset",
      "name": "LLM",
      "termCode": "llm",
      "url": "https://wavect.io/zh/glossary/llm/"
    },
    {
      "@id": "https://wavect.io/zh/glossary/llm/#webpage",
      "@type": "WebPage",
      "about": {
        "@id": "https://wavect.io/#organization",
        "@type": [
          "Organization",
          "ProfessionalService",
          "LocalBusiness"
        ]
      },
      "author": {
        "@id": "https://wavect.io/team/kevin-riedl/#person",
        "@type": "Person",
        "name": "Kevin Riedl",
        "url": "https://wavect.io/team/kevin-riedl/"
      },
      "dateModified": "2026-06-02",
      "description": "一种经过训练以预测下一个 token 的统计模型，这使它在语言任务上出奇地出色，而在任何需要保证正确性的事情上都不可靠。",
      "headline": "LLM",
      "inLanguage": "zh",
      "isPartOf": {
        "@id": "https://wavect.io/#website",
        "@type": "WebSite"
      },
      "lastReviewed": "2026-06-02",
      "mainEntity": {
        "@id": "https://wavect.io/zh/glossary/llm/#term"
      },
      "mentions": [
        {
          "@id": "https://wavect.io/#organization",
          "@type": [
            "Organization",
            "ProfessionalService",
            "LocalBusiness"
          ]
        },
        {
          "@type": "Service",
          "name": "人工智能",
          "url": "https://wavect.io/zh/services/artificial-intelligence/"
        }
      ],
      "name": "LLM",
      "reviewedBy": {
        "@id": "https://wavect.io/team/christof-jori/#person",
        "@type": "Person",
        "name": "Christof Jori",
        "url": "https://wavect.io/team/christof-jori/"
      },
      "speakable": {
        "@type": "SpeakableSpecification",
        "cssSelector": [
          ".gls-single__h1",
          ".gls-single__tldr"
        ]
      },
      "url": "https://wavect.io/zh/glossary/llm/"
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "item": "https://wavect.io/zh/",
          "name": "首页",
          "position": 1
        },
        {
          "@type": "ListItem",
          "item": "https://wavect.io/zh/glossary/",
          "name": "技术、产品与合作模式术语表",
          "position": 2
        },
        {
          "@type": "ListItem",
          "item": "https://wavect.io/zh/glossary/llm/",
          "name": "LLM",
          "position": 3
        }
      ]
    }
  ]
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    {
      "@type": "Question",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "一种根据已有文本预测下一段文本的模型。在足够的数据上训练后，这种预测会产生流畅、有用的回答。它是大规模的模式补全，而不是理解。"
      },
      "name": "用简单的话说，什么是 LLM？"
    },
    {
      "@type": "Question",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "当你需要保证正确且可审计的答案时。LLM 是概率性的，所以对于税务计算、合规逻辑，或任何自信的错误答案会带来危险的场景，应使用确定性代码，让 LLM 只在边缘处辅助。"
      },
      "name": "什么时候 LLM 是错误的工具？"
    },
    {
      "@type": "Question",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "只知道到其训练截止日期为止的内容。任何更新的内容，或任何与你业务相关的具体内容，除非你在运行时通过检索把上下文喂给它，否则它都不知道。"
      },
      "name": "LLM 知道当前事件吗？"
    }
  ],
  "speakable": {
    "@type": "SpeakableSpecification",
    "cssSelector": [
      ".faq-question",
      ".faq-answer"
    ]
  }
}
```