A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting 事件

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting arXiv:2606.03280v1 Announce Type: new Abstract: Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training. We ask whether a more direct and stricter channel is also viable: can one language model communicate useful intermediate reasoning state to another at inference time by translating and injecting hidden activations, rather than by passing n