SOURCE-LINKED INTELLIGENCE

How Calibration Content Shapes Attention-Based Reranking

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional and structural bias. Although widely used, this calibration assumes that the null pass removes irrelevant signal from each document. We show that modern prompt content, e.g. constraints, instructions, personas, and demonstrations can violate this assumption when it enters the scoring readout, making the null pass relevance-aware rather than null. We find that calibration is especially harmful when applied to prompts containing longer, more deta

Read original source ↗ Open in workspace

recordType

paper

region

Global