generative-ranking

This paper introduces hLLM, a decoding strategy for generative reranking that uses the Hungarian algorithm to achieve single-pass decoding, resulting in a 64x speed-up while maintaining ranking quality.

PRISMR proposes a framework using hypernetworks and LoRA to internalize list structure, overcoming parse collapse in multimodal listwise ranking. It introduces a large-scale benchmark and shows reduced parse collapse and improved ranking performance across domains and backbones.