Unverified50% confidenceFactExact time
Taking RAG as an example, interviewers will follow up by asking why Fine-tuning was not used, how to optimize when retrieval recall rate is low, and which vector database was used and why.
1
Sources
50%
Confidence
Long-term
Relevance
9/22/2026
First Seen
Sources
Related Entities
Related Claims
Unverified企业RAG项目中回答质量不佳的原因可能来自文档切分策略、Embedding模型选择、检索算法精度和Prompt模板设计等多个环节78% similarVerifiedRAG (Retrieval-Augmented Generation) solutions based on vector databases are better suited for handling document-type knowledge, but often fall short in retrieval precision and real-time performance for highly structured engineering facts.74% similarUnverifiedChunks that are too large dilute retrieval precision, while chunks that are too small result in incomplete semantics; the chunking strategy directly determines the retrieval quality of a RAG system.73% similarUnverifiedResearch indicates that in RAG systems, the quality of the retrieval stage often has a greater impact on final answer accuracy than the gains brought by the language model's own scale.72% similarUnverified相比RAG提交prompt有硬上限，图谱工具调用允许模型按需调用任意次数以挖掘所需信息71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/941777API
curl https://kongchang.com/api/v1/knowledge/claims/941777MCP
get_claim(id=941777)