[KongchangAI]
Unverified50% confidenceFactExact time

The identification and refusal of compositional harm are decoupled: nine standard direction-finding methods detect compositional harm with an AUC of up to 0.99, but ablating these directions either does not affect refusal behavior or destroys model coherence.

1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1141925
API
curl https://kongchang.com/api/v1/knowledge/claims/1141925
MCP
get_claim(id=1141925)