Unverified50% confidenceFactExact time
At the global level, IAU-FOA uses a cosine similarity-based objective function to reduce the global semantic gap between adversarial examples and target samples.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在特定垂直领域语料上微调的Embedding模型往往能提升同义查询相似度得分，降低阈值误判率67% similarUnverifiedCosine similarity measures the cosine of the angle between two vectors, normalizes by the magnitude of the vectors in the denominator, and completely ignores vector magnitude while only caring about direction.65% similarUnverifiedThe embedding layer and language model head are most sensitive to quantization precision degradation, while intermediate FFN layers have stronger redundancy tolerance.65% similarUnverifiedDelegating numerical calculations to code rather than to an LLM yields reproducible results, which is a manifestation of the separation-of-concerns principle in AI applications64% similarUnverifiedUsing FSM states as context for a next-step prediction task outperformed Agent Workflow Memory (AWM) on every dataset with ground-truth matches.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983380API
curl https://kongchang.com/api/v1/knowledge/claims/983380MCP
get_claim(id=983380)