AI/ ai · llm-research · multimodal-ai · ai-evaluation

Splitting AI Review Into Two Passes Curbs Dropped Content

Splitting AI review into two passes cuts dropped content by roughly a third, but researchers call it a mitigation, not a cure, since two failure modes remain.

Ask a multimodal AI model to review a long recording or document in one shot, and it will quietly skip about a third of it.

New research tests what happens when a multimodal model reviews long sources in a single pass versus two. The one-pass approach drops roughly a third of the content and pads the rest with embellishment, and it is not a perception problem: the same dropped material reappears when the model is simply asked to transcribe the source. The bottleneck is capacity: one pass can't perceive, reason, and write a faithful long review at the same time, and even a much larger reasoning budget doesn't help, because the model spends it planning a review instead of transcribing the source. Splitting the job into two passes with the same model weights, first transcribing then reviewing the transcript, improved both faithfulness and coverage across a 21-source test suite.

This is a structural fix for a problem you can't prompt your way out of, since more reasoning time just makes the model plan a review of content it hasn't written down yet. It matters for anyone using AI to summarize meetings, contracts, or scanned documents, where losing a third of the material is the difference between a useful summary and a liability. It also suggests the industry's habit of throwing bigger reasoning budgets at problems is solving the wrong one here.

Still, the researchers call this a mitigation, not a cure: the review pass can run out of room on very long sources, and once the transcript is out of context, the model can start confabulating from memory anyway.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →