Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time 事件

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time arXiv:2606.01923v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations. Existing mitigation strategies primarily rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanism