Unverified50% confidenceDecision RuleExact time
Recall's core rule is: if the model cannot cite a certain node, it may not state the corresponding conclusion.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt engineering cannot defend against prompt injection in principle, so authorization logic must be placed outside the model.71% similarUnverifiedDeterministic structured facts should not be left to the model to memorize or infer, but should be read and written by explicit rules.70% similarVerifiedWhen the model itself lacks the capability to understand a specific problem, no amount of prompt engineering can compensate for this deficiency70% similarUnverifiedExperiments found that a meta-model trained on word-level features could not predict which words should be removed, indicating that there is no targetable objective for fine-tuning stopword lists.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062569API
curl https://kongchang.com/api/v1/knowledge/claims/1062569MCP
get_claim(id=1062569)