SOURCE-LINKED INTELLIGENCE

Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Draft-verify-revise is a common LLM orchestration pattern for scaling inference-time compute. One LLM drafts, a second critiques the draft and provides feedback, and a third uses that feedback to revise the draft into the final output. As context cascades between stages, LLMs at different stages can resolve a context-dependent expression such as "previous" differently. When that happens, the expression undergoes a deictic shift, a change in what it refers to. This phenomenon was studied with a synthetic dataset of 10 base examples, each rendered in three conditions. Holding the shared componen

Read original source ↗ Open in workspace

recordType

paper

region

Global