SOURCE-LINKED INTELLIGENCE

Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

When a context asserts two values for one fact, a model commits to a cue -- recency, repetition, position -- but natural data rarely makes these disagree, so behavior cannot reveal which. We train 26M-parameter transformers on a synthetic language where recency and rarity are exactly coextensive, and separate them with a minimal causal edit that inverts one cue while holding the truth, token count and answer position fixed. All 75 runs reach accuracy >= 0.999, including where the trivial heuristic fails, so no held-in evaluation distinguishes them. Under intervention the per-cell readout does

Read original source ↗ Open in workspace

recordType

paper

region

Global