Reranking

Semantic retrieval and keyword retrieval are often used together in mature RAG systems (hybrid retrieval), then results are optimized through a reranking model, to balance recall and precision.

Reranking uses a cross-encoder to score query-document pairs one by one, with accuracy far higher than vector similarity but at higher computational cost, so fine ranking is done only on the small number of candidates after coarse ranking, forming a two-stage architecture of coarse ranking plus fine ranking.

It is predicted that reranking, information extraction, and content moderation are the next batch of LLM-facing workloads to be "unbundled", with specialized small models replacing general-purpose large models and forming price competition.

The essence of reranking is to rebalance recall rate and precision rate, serving as a bridge component between retrieval and generation.

Before multi-path retrieval results enter reranking, they typically need to undergo deduplication and score normalization; otherwise, inconsistent score scales across different retrieval paths will introduce bias.

Increasing re-ranking intensity or optimizing chunking strategies cannot compensate for the absence of the underlying data structure.

Multi-channel retrieval simultaneously fetches candidate results through multiple different retrieval channels and then performs fusion ranking to maximize recall rate.

Reranking is typically implemented using cross-encoders, which concatenate the query and candidate documents before feeding them in together; it usually reranks only the Top-50 to Top-100 candidates and finally selects Top-3 to Top-5 to pass to the generative model.

重排序（Re-ranking）机制在初步检索后引入交叉编码器（Cross-Encoder）对候选文档重新打分，提升输入大模型的上下文质量