How Calibration Content Shapes Attention-Based Reranking

2026-09-15

AI Summary

研究解决了注意力重排序中的校准问题，通过提出插值空校准方法来控制指令内容对空基线的影响，从而在指令密集任务中恢复性能。

Abstract

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 detailed instructions as the null-pass step removes relevant signal. Based on these findings, we propose interpolated null calibration, a training-free modification that controls how much of the instruction content enters the null baseline. It recovers attention-based reranking performance on instruction-heavy tasks where standard calibration fails, while preserving calibration's benefits when the null pass remains relevance-agnostic. On instruction heavy tasks, the recovered rankings surpass generative rerankers. We also show that in-context demonstrations improve attention-based reranking with little calibration interference, since demonstrations act only through the query pass and leave the null pass unchanged.

Problem

• Attention-based Reranking
• Calibration Content
• Instruction-heavy Tasks
• Relevance Signal
• Null Pass

Innovation

• interpolated null calibration
• attention-based reranking
• instruction-heavy tasks