Unverified50% confidenceOpinionExact time
The limitations of vector retrieval include that retrieval quality depends on the semantic understanding capability of the embedding model, and it cannot guarantee the recall of all key information, posing a risk of memory omission.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen semantically similar but inaccurate content is retrieved, the model may output incorrect recollections with high confidence, with no warning mechanism at the system level — this is the false memory problem.74% similarUnverifiedLimitations of RAG include that poor quality of retrieved documents, retrieval failures, and the model ignoring retrieved evidence (attention drift) can still lead to hallucinations.74% similarUnverifiedThe root cause of poor knowledge base performance typically lies in unreasonable document chunking strategies, inappropriate vector model selection, or insufficient retrieval recall quantity, rather than issues with the model itself.74% similarUnverifiedFine-tuning is not suitable as memory because retraining every time new user data is added is extremely costly, and a fine-tuned model makes it hard to precisely delete a piece of information or to guarantee per-user isolation.73% similarUnverifiedThe essence of information overload is often not too much information, but the lack of an effective filtering mechanism.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1089236API
curl https://kongchang.com/api/v1/knowledge/claims/1089236MCP
get_claim(id=1089236)