Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration

ArXi:2604.10150v1 Announce Type: new Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural sensitivity to input order independent of relevance. Existing mitigations present a dilemma: inference-time aggregation incurs prohibitive latency, while