Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models

ArXi:2604.02315v2 Announce Type: replace Standard LLM benchmarks evaluate the assistant turn: the model generates a response to an input, a verifier scores correctness, and the analysis ends. This paradigm leaves unmeasured whether the LLM encodes any awareness of what follows the assistant response. We propose user-turn generation as a probe of this gap: given a conversation context of user query and assistant response, we let a model generate under the user role.