מנגנון תפיסה מותאם לחיפוש לריבונדינג דינמי לעקוב אחר גופים במודלי שפה גדולים

תקציר מקורי באנגליתarXiv:2606.08644v2 Announce Type: replace Abstract: To interpret context correctly and retrieve relevant information, large language models must bind entities to their attributes and update these bindings as state changes. We analyze how LLMs implement this binding process in a dynamic state tracking. Using causal interventions, we identify a retrieval conditioned rebinding mechanism, a compact attention head circuit that propagated binding information and when the entity is queried, uses the updated binding to retrieve the corresponding attribute. Across Gemma and Llama models, this circuit supports rebinding behavior, but the representational signature of the mechanism differs across model families. In Gemma models, the binding signature is clearly expressed in the query/key subspaces of