GraphRAG：负责任的 AI 常见问题解答

What is GraphRAG?  什么是 GraphRAG？

GraphRAG is an AI-based content interpretation and search capability. Using LLMs, it parses data to create a knowledge graph and answer user questions about a user-provided private dataset.
GraphRAG 是一款基于 AI 的内容解读和搜索工具。它使用 LLM 解析数据，创建知识图谱，并解答用户关于其提供的私有数据集的问题。

What can GraphRAG do?  GraphRAG 能做什么？

GraphRAG is able to connect information across large volumes of information and use these connections to answer questions that are difficult or impossible to answer using keyword and vector-based search mechanisms. Building on the previous question, provide semi-technical, high-level information on how the system offers functionality for various uses. This lets a system using GraphRAG to answer questions where the answers span many documents as well as thematic questions such as “what are the top themes in this dataset?.”
GraphRAG 能够将海量信息连接起来，并利用这些连接来解答那些使用关键词和基于向量的搜索机制难以或无法解答的问题。基于上一个问题，提供半技术性的、高级的信息，说明该系统如何为各种用途提供功能。这使得使用 GraphRAG 的系统能够回答跨多个文档的问题，以及诸如“这个数据集中的热门主题是什么？”之类的主题问题。

What are GraphRAG’s intended use(s)?
GraphRAG 的预期用途是什么？

• GraphRAG is intended to support critical information discovery and analysis use cases where the information required to arrive at a useful insight spans many documents, is noisy, is mixed with mis and/or dis-information, or when the questions users aim to answer are more abstract or thematic than the underlying data can directly answer.
  GraphRAG 旨在支持关键信息发现和分析用例，其中获得有用见解所需的信息跨越许多文档、嘈杂、混杂有错误和/或虚假信息，或者当用户想要回答的问题比底层数据可以直接回答的更抽象或主题化时。
• GraphRAG is designed to be used in settings where users are already trained on responsible analytic approaches and critical reasoning is expected. GraphRAG is capable of providing high degrees of insight on complex information topics, however human analysis by a domain expert of the answers is needed in order to verify and augment GraphRAG’s generated responses.
  GraphRAG 的设计目标是用于用户已接受过负责任的分析方法培训并具备批判性推理能力的场景。GraphRAG 能够对复杂的信息主题提供高度的洞察力，但为了验证和增强 GraphRAG 生成的响应，需要由领域专家对答案进行人工分析。
• GraphRAG is intended to be deployed and used with a domain specific corpus of text data. GraphRAG itself does not collect user data, but users are encouraged to verify data privacy policies of the chosen LLM used to configure GraphRAG.
  GraphRAG 旨在与特定领域的文本数据语料库一起部署和使用。GraphRAG 本身不收集用户数据，但鼓励用户验证用于配置 GraphRAG 的所选 LLM 的数据隐私政策。

How was GraphRAG evaluated? What metrics are used to measure performance?
GraphRAG 是如何评估的？使用哪些指标来衡量其性能？

GraphRAG has been evaluated in multiple ways. The primary concerns are 1) accurate representation of the data set, 2) providing transparency and groundedness of responses, 3) resilience to prompt and data corpus injection attacks, and 4) low hallucination rates. Details on how each of these has been evaluated is outlined below by number.
GraphRAG 已通过多种方式进行评估。主要关注点包括：1）数据集的准确表示；2）响应的透明度和可靠性；3）对提示和数据集注入攻击的抵御能力；以及 4）低幻读率。以下按编号概述了各项评估的详情。

1. Accurate representation of the dataset has been tested by both manual inspection and automated testing against a “gold answer” that is created from randomly selected subsets of a test corpus.
   已经通过手动检查和自动测试对数据集的准确表示进行了测试，测试依据是从测试语料库中随机选择的子集创建的“黄金答案”。

2. Transparency and groundedness of responses is tested via automated answer coverage evaluation and human inspection of the underlying context returned.
   通过自动答案覆盖率评估和对返回的底层上下文的人工检查来测试答案的透明度和依据。

3. We test both user prompt injection attacks (“jailbreaks”) and cross prompt injection attacks (“data attacks”) using manual and semi-automated techniques.
   我们使用手动和半自动技术测试用户提示注入攻击（“越狱”）和交叉提示注入攻击（“数据攻击”）。

4. Hallucination rates are evaluated using claim coverage metrics, manual inspection of answer and source, and adversarial attacks to attempt a forced hallucination through adversarial and exceptionally challenging datasets.
   幻觉率是使用索赔覆盖率指标、答案和来源的手动检查以及对抗性攻击来评估的，以尝试通过对抗性和极具挑战性的数据集强制产生幻觉。

What are the limitations of GraphRAG? How can users minimize the impact of GraphRAG’s limitations when using the system?
GraphRAG 有哪些局限性？用户在使用系统时如何最大限度地减少 GraphRAG 局限性带来的影响？

GraphRAG depends on a well-constructed indexing examples. For general applications (e.g. content oriented around people, places, organizations, things, etc.) we provide example indexing prompts. For unique datasets effective indexing can depend on proper identification of domain-specific concepts.
GraphRAG 依赖于精心构建的索引示例。对于一般应用（例如，围绕人物、地点、组织、事物等的内容），我们提供示例索引提示。对于特殊数据集，有效的索引可能取决于对特定领域概念的正确识别。

Indexing is a relatively expensive operation; a best practice to mitigate indexing is to create a small test dataset in the target domain to ensure indexer performance prior to large indexing operations.
索引是一种相对昂贵的操作；缓解索引的最佳实践是在目标域中创建一个小型测试数据集，以确保在进行大型索引操作之前索引器的性能。

What operational factors and settings allow for effective and responsible use of GraphRAG?
哪些操作因素和设置可以有效且负责任地使用 GraphRAG？

GraphRAG is designed for use by users with domain sophistication and experience working through difficult information challenges. While the approach is generally robust to injection attacks and identifying conflicting sources of information, the system is designed for trusted users. Proper human analysis of responses is important to generate reliable insights, and the provenance of information should be traced to ensure human agreement with the inferences made as part of the answer generation.
GraphRAG 专为具备丰富领域知识且经验丰富的用户设计，帮助他们应对复杂的信息挑战。虽然该方法通常能够有效抵御注入攻击并识别冲突的信息源，但该系统专为值得信赖的用户设计。对答案进行适当的人工分析对于生成可靠的见解至关重要，并且应追溯信息的来源，以确保人工与答案生成过程中做出的推论相符。

GraphRAG yields the most effective results on natural language text data that is collectively focused on an overall topic or theme, and that is entity rich – entities being people, places, things, or objects that can be uniquely identified.
GraphRAG 在自然语言文本数据上产生最有效的结果，这些数据集中于一个总体话题或主题，并且实体丰富——实体是可以唯一识别的人、地点、事物或物体。

While GraphRAG has been evaluated for its resilience to prompt and data corpus injection attacks, and has been probed for specific types of harms, the LLM that the user configures with GraphRAG may produce inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case and model. Developers should assess outputs for their context and use available safety classifiers, model specific safety filters and features (such as https://azure.microsoft.com/en-us/products/ai-services/ai-content-safety), or custom solutions appropriate for their use case.
虽然 GraphRAG 已针对其对提示和数据语料库注入攻击的抵御能力进行了评估，并针对特定类型的危害进行了探索，但用户使用 GraphRAG 配置的 LLM 可能会生成不适当或令人反感的内容，如果没有针对用例和模型的额外缓解措施，这可能使其不适合在敏感环境中部署。开发人员应根据其具体情况评估输出，并使用可用的安全分类器、特定于模型的安全过滤器和功能（例如 https://azure.microsoft.com/en-us/products/ai-services/ai-content-safety ）或适合其用例的自定义解决方案。

引用原文：

graphrag/RAI_TRANSPARENCY.md at main · microsoft/graphrag · GitHub