Morning Edition · Tuesday, June 30, 2026Published at 6:59 AM EDT · New York

A Theory Paper Asks Whether Language Models Can Learn While Hallucinating Forever

New work extends the classic 'generation in the limit' framework to ask what happens when a learner never stops producing invalid strings.

A theoretical contribution, Generating in the Limit with Infinitely Many Hallucinations, works in the formal model of language learning as a game between an adversary, which reveals strings from an unknown target language, and a learner tha…