Unverified50% confidenceFactExact time
In retrieval-augmented generation (RAG) scenarios, additions, deletions, and modifications of knowledge base documents directly change the context available to the agent, thereby affecting output quality.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
Unverified如果RAG检索源被操纵（如通过SEO让特定立场内容排名靠前），模型输出将直接受到影响78% similarVerifiedRetrieval-Augmented Generation (RAG) anchors facts by incorporating real-time web search with cited sources, but its effectiveness is influenced by factors such as search result quality, document parsing accuracy, and the model's comprehension capability.78% similarUnverifiedDifferent phrasings of user queries will generate different vectors, and the semantic distance from document content will also vary, affecting RAG retrieval performance.74% similarVerifiedFine-tuning burns knowledge into model weights, making knowledge updates costly as they require retraining; RAG stores knowledge in an external database, so updates only require modifying the database without changing the model.74% similarUnverifiedIn RAG scenarios, the retrieved context changes with every query, and if it is placed early in the prompt it breaks cache hits for subsequent content, so the static system prompt is usually placed first to benefit from caching, with dynamic retrieved document chunks placed later.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049090API
curl https://kongchang.com/api/v1/knowledge/claims/1049090MCP
get_claim(id=1049090)