SOURCE-LINKED INTELLIGENCE

Record Grouping Controls Evidence Weight in Language Models

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Retrieved records are presentation units; a supplied partition determines which records enter a language model as one evidential contribution. We characterize the invariant group-content state that removes within-group copies while retaining complementary canonical content, show that equal group counts can encode different evidence states, and derive a sharp content-aware partition-error bound. Given a supplied partition, our pre-generation representation deduplicates and aggregates content within groups and bounds each group's contribution. Across 104,402 trials and 6 public checkpoints, a ce

Read original source ↗ Open in workspace

recordType

paper

region

Global