[KongchangAI]
Unverified50% confidenceFactExact time

研究团队以Llama-3.1-8B-Instruct模型为实验对象,在3个留出的欺骗检测数据集上考察探针泛化性能

1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/899111
API
curl https://kongchang.com/api/v1/knowledge/claims/899111
MCP
get_claim(id=899111)