Split the Labor: Separating Evidence Interpretation from Decision Aggregation
Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt. This conflates two operations with different requirements. Interpreting a source rewards capacity and context. Combining interpretations rewards fixed arithmetic, comparability across instances, and the option to return nothing. Once separated, the design problem becomes the…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
