ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

ArXi:2506.03487v2 Announce Type: replace-cross Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters), presenting high computational costs. Small Language Models (SLMs) offer a promising alternative because of computational efficiency.