Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token
Under stochastic decoding, a single context can elicit many different answers from a language model. Characterizing this variation typically requires many expensive autoregressive rollouts, each revealing only one realization. We ask whether the activations produced while reading the context can directly forecast the model's rollout activations. We train context--answer metamodels that map a…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
