Grounding — процесс связывания выхода ИИ-модели с надежными, проверяемыми источниками информации во время инференса. В генеративном ИИ он помогает повышать фактическую надежность, предоставляя релевантный контекст без изменения базовых весов модели. Retrieval-augmented generation является распространенной техникой grounding.
The process of basing all or part of an LLM's response on information retrieved from one or more trusted sources. For example, suppose a user prompts an LLM for today's weather forecast in Berlin. The LLM might ground the response on information it gathers from the European Centre for Medium-Range Weather Forecasts. Retrieval-augmented generation (RAG) is a common grounding technique.
The process of connecting a model's output to verifiable sources of information. Grounding helps to improve the accuracy, reliability, and usefulness of AI outputs by providing the model with access to specific data sources, and reduces the likelihood of hallucinations. A common type of grounding is retrieval-augmented generation (RAG).