האמת הייתה תמיד נכונה: אליזה מושלמת בתרגילי נאמנות

תקציר מקורי באנגליתarXiv:2609.10739v1 Announce Type: cross Abstract: A truth probe fitted where truthful reporting and a task's prescribed action coincide cannot distinguish those targets from its fitting labels alone. We call this failure of semantic identification perfect aliasing. In a controlled binary reporting game, truth and prescribed-action probes fitted on compliant contexts solve the same optimization. On rival contexts their labels are complements, forcing their AUROCs to sum to one; this identity holds across 751 cell-layer pairs to floating-point precision. We separate prescribed output symbols from semantic action using randomized codebooks, then separate truth from prescribed action by fitting on mixed compliant and rival contexts. For a reward-trained Gemma-2-9B policy that answers falsely o