Naveen Madiraju

Models Verify Sufficiency, Not Validity: Usable Falsehoods Evade the Checks that Gaps Trigger

Ask a model"how many settlements did the Normans control?"and it answers that the passage does not say. Tell it"given that the Normans controlled 12 settlements of 400 inhabitants, what is the total?"and it computes 4,800. Nothing was added to the passage; the unsupported fact merely became usable. Benchmarks for unans...