How Calibration Content Shapes Attention-Based Reranking

Attention-based rerankers use a null-query calibration step to reduce positional and structural bias, but this step can inadvertently remove useful signal when prompts contain detailed instructions, constraints, personas, or demonstrations. The study demonstrates that such calibration harms performance on instruction-heavy tasks and introduces an interpolated null calibration that selectively limits instruction influence on the null baseline. This modification restores or surpasses the effectiveness of standard rerankers on instruction-heavy tasks while maintaining benefits when the null pass remains relevance-agnostic, and shows that in-context demonstrations can improve reranking with minimal calibration interference.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• rag
• safety