התגברות על התנהגויות שקריות ב-LLMs באמצעות קבוצות זיכרון נגדיות

תקציר מקורי באנגליתarXiv:2609.38909v1 Announce Type: new Abstract: Large language models often know the truth and say otherwise: a model that answers correctly when asked neutrally will affirm a user's mistaken belief, or misstate a fact its system prompt wants hidden, once the context rewards it. Such deception is a behavior conditioned on context, not knowledge, yet machine unlearning, the natural tool for removing a behavior from the weights, is built to forget facts that a deceptive model still needs. We propose to unlearn when a model deceives rather than what it knows, with a contrastive forget unit built from the model's own realized deceptions: the same question under a deception-triggering and a neutral context, admitted only where belief holds and behavior flips. Standard objectives on this unit fa