---
title: "Hybrid retrieval — 混合检索"
source: "https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2"
wiki: "systems-analysis.info/int"
article: "Hybrid_retrieval_—_混合检索"
language: "zh"
categories:
  - "Category:Chinese"
  - "Category:Large language models"
  - "Category:Prompt engineering"
revision_id: 3104
wiki_created_at: 2026-09-06T23:15:45Z
wiki_modified_at: 2026-09-06T23:15:45Z
downloaded_at: 2026-09-07T22:55:10Z
---

# Hybrid retrieval — 混合检索

**Hybrid Retrieval（混合检索）** — 是一类信息检索方法，它结合了词法（稀疏）和语义（密集/后期交互）信号，以提高检索结果的召回率和准确性。混合方案结合了精确术语匹配（BM25/TF-IDF）和向量相似度（双编码器、后期交互多向量模型）的优点，并采用对不同尺度得分具有鲁棒性的排序融合方法（例如，倒数排序融合 Reciprocal Rank Fusion, CombSUM/CombMNZ）以及交叉编码器重排。<sup>[\[1\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-1)[\[2\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-2)[\[3\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-3)</sup>

## 定义与动机

*混合检索*是一种通过两个（或更多）独立信号通道进行并行或级联搜索，然后进行结果融合和/或重排的方法。典型动机包括：(i) 克服“术语鸿沟”（如同义词、改写）；(ii) 应对拼写错误/形态变化；(iii) 提取特定代码/标识符（稀疏模型的强项）；(iv) 迁移到新领域/语言（密集模型提供语义泛化能力）。<sup>[\[4\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-4)[\[5\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-5)[\[6\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-6)</sup>

## 混合检索的组成部分

### 词法（稀疏）检索

- **经典模型。** TF-IDF 和 BM25/BM25F 是基于倒排索引的标准基线方法；BM25 在概率相关性框架（PRF）中得到理论支持，并广泛用于第一阶段排序。<sup>[\[7\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-7)</sup>
- **可学习的稀疏模型。**
  - **SPLADE / SPLADE++/v3。** 一种神经稀疏模型，通过带有稀疏性正则化的 MLM 头来学习词项的扩展和加权；在多个基准（如 BEIR）上表现出强大的性能和良好的泛化能力。<sup>[\[8\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-8)[\[9\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-9)[\[10\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-10)</sup>
  - **uniCOIL/COIL。** 上下文感知的倒排列表及其简化版本 *uniCOIL*；与传统倒排索引兼容。<sup>[\[11\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-11)</sup>

### 语义（密集/后期交互）检索

- **双编码器（Bi-encoder / single-vector）。** 查询和文档被编码为向量，相似度通过点积（dot-product）或最大内积搜索（MIPS）计算。例如：DPR,<sup>[\[12\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-12)</sup> ANCE,<sup>[\[13\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-13)</sup> Contriever,<sup>[\[14\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-14)</sup> GTR,<sup>[\[15\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-15)</sup> E5。<sup>[\[16\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-16)</sup>
- **后期交互（Late-interaction / multi-vector）。** 在“后期”交互阶段对词元级别的匹配进行建模，如 ColBERT/ColBERTv2；其权衡在于以更大的索引和延迟换取更高的准确性，可通过 PLAID、WARP 等工程驱动优化。<sup>[\[17\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-17)[\[18\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-18)[\[19\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-19)</sup>

## 混合与排序融合方案

- **并行搜索与候选集合并。** 独立地从稀疏和密集通道获取候选列表及其内部得分，然后进行排序融合。<sup>[\[20\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-20)</sup>
- **RRF (Reciprocal Rank Fusion)。** 一种对不可比较的排序分数具有鲁棒性的技术，通过对排名的倒数求和进行融合：

${RRF}(d) = \sum\limits_{i = 1}^{m}\frac{1}{k + {rank}_{i}(d)}$，其中 \`k\` 通常取 60 左右。<sup>[\[21\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-21)</sup> 该方法作为内置检索器/处理器在 Elasticsearch/OpenSearch 等工业级搜索引擎中得到支持。<sup>[\[22\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-22)[\[23\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-23)</sup>

- **CombSUM/CombMNZ 等。** 经典的“分数求和”函数（必要时进行归一化）。<sup>[\[24\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-24)[\[25\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-25)[\[26\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-26)</sup>
- **加权线性组合。**

$S(d) = \alpha \cdot S_{\text{sparse}}(d) + (1 - \alpha) \cdot S_{\text{dense}}(d)$, $\alpha \in \lbrack 0,1\rbrack$。\`α\` 的选择可以是固定的，也可以是可学习的（基于数据集/查询）。<sup>[\[27\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-27)</sup>

- **分数归一化。** 对于 CombSUM/CombMNZ，通常采用 min-max、z-score 等方法来统一尺度；<sup>[\[28\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-28)</sup> 而 RRF 则仅依赖于排名。
- **动态/自适应加权。** 查询路由（query routing）、查询特征以及 LTR 模型可用于选择或加权不同通道；最新研究表明，一个简单的经过学习的线性组合通常优于 RRF，并且对分数归一化不敏感。<sup>[\[29\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-29)</sup>

## 重排与多阶段流水线

混合系统通常构建为 *retrieval → fusion → rerank*（检索 → 融合 → 重排）的流水线。重排阶段采用：

- **交叉编码器（Cross-encoders，如 BERT/T5）。** 准确性最高，但计算成本高：MonoBERT/MonoT5 用于对前 N 个候选结果进行重排序。<sup>[\[30\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-30)[\[31\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-31)</sup>
- **后期交互模型作为重排器。** ColBERT 系列模型也可以用作重排器；现代加速器（如 PLAID、WARP）能在不损失质量的情况下降低延迟。<sup>[\[32\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-32)[\[33\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-33)</sup>

在 RAG 和严格的服务等级协议（SLA）场景下，*质量 ↔ 延迟/成本*的权衡尤为重要（参见 p95/p99 尾部延迟）。<sup>[\[34\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-34)</sup>

## 基准评测

- **BEIR。** 一个统一的数据集集合，包含来自不同领域和任务的数据，用于对检索器进行零样本/域外（zero-/out-of-domain）评估（例如，TREC-COVID, NFCorpus, NQ, HotpotQA, FiQA-2018, DBPedia-entity, ArguAna, Webis-Touché-2020, FEVER/Climate-FEVER, Scidocs, SciFact, CQADupStack 等）。<sup>[\[35\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-35)</sup>
- **TREC Deep Learning / MS MARCO。** 用于在大数据模式下训练和评估检索器与重排器的经典资源。<sup>[\[36\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-36)[\[37\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-37)[\[38\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-38)</sup>
- **质量指标。** nDCG@k, Recall@k, MRR；**性能指标**——延迟 p50/p95/p99, QPS；**运营指标**——内存/成本（CPU/GPU，索引）。<sup>[\[39\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-39)[\[40\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-40)</sup>
- **消融研究。** 建议明确每个通道/权重的贡献，以及对 RRF 中的 \`k\` 和混合权重 \`α\` 的敏感性；评估模型对查询改写和 OOD（域外）数据偏移的鲁棒性。<sup>[\[41\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-41)[\[42\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-42)</sup>

## 工程实现与生产实践

- **索引与 ANN。** FAISS (Flat/HNSW/IVF-PQ), HNSW, ScaNN 用于 MIPS/余弦相似度搜索。<sup>[\[43\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-43)[\[44\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-44)[\[45\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-45)</sup>
- **IR 技术栈。** Lucene/Anserini/Pyserini 用于稀疏/密集和混合检索流水线；在 BEIR 上具有“一键式”可复现性。<sup>[\[46\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-46)[\[47\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-47)</sup>
- **向量数据库与搜索引擎。** Qdrant, Weaviate, pgvector/PostgreSQL, Vespa, Elasticsearch/OpenSearch 均提供原生混合搜索模式（BM25F+向量）和/或 RRF/线性组合功能。<sup>[\[48\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-48)[\[49\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-49)[\[50\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-50)[\[51\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-51)[\[52\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-52)</sup>
- **RAG 模式。** 架构：**检索 → 融合 → 重排 → LLM 上下文**，并需考虑词元限制和来源追溯。<sup>[\[53\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-53)</sup>
- **索引更新、去重、分词。** 协调 BM25 和向量化模型的分词器至关重要；在混合前对得分进行校准（归一化/缩放）。<sup>[\[54\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-54)</sup>

## 局限性与开放问题

- **可移植性与多语言支持。** 密集模型（如 GTR/E5）提升了迁移能力，但对领域/语言敏感；稀疏模型（如 SPLADE）在 OOD 场景下通常更鲁棒。<sup>[\[55\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-55)[\[56\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-56)</sup>
- **与 LLM 的集成及幻觉问题。** 混合检索减少了 RAG 上下文中的信息遗漏和噪声，但不能完全消除幻觉；需要严格的重排器和来源过滤。<sup>[\[57\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-57)</sup>
- **成本与隐私。** 多向量索引的存储、压缩、加密和本地化（on-prem）部署；总拥有成本（TCO）评估。
- **发展趋势。** HyDE/doc2query/PRF 作为文档/查询扩展技术；<sup>[\[58\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-58)[\[59\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-59)</sup> 混合权重学习（per-query \`α\`）、更高效的后期交互模型（PLAID/WARP）、长文档处理和多向量索引。<sup>[\[60\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-60)[\[61\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-61)</sup>

## 方法对比表

截至 2025-09-10（基于 BEIR *trec-covid* 数据集的示例；nDCG@10 / Recall@100）：<sup>[\[62\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-62)</sup>

| 方法                         | 类型 (稀疏/密集/混合) | 思路/模型               | 融合方案              | 重排器               | nDCG@10 / R@100                    | 延迟 (相对) | 来源                                                                                                                                                                                                                                                                                                                                                                                |
|------------------------------|-----------------------|-------------------------|-----------------------|----------------------|------------------------------------|-------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| BM25                         | 稀疏                  | 精确词项匹配 (PRF/BM25) | —                     | —                    | 0.595 / 0.109                      | 非常低      | <sup>[\[63\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-63)[\[64\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-64)</sup>                                                                                                                         |
| SPLADE++ (ED)                | 稀疏 (可学习)         | 稀疏词项扩展/加权       | —                     | —                    | 0.727 / 0.128                      | 低–中       | <sup>[\[65\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-65)[\[66\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-66)</sup>                                                                                                                         |
| Contriever (MS MARCO FT)     | 密集                  | 对比学习双编码器        | —                     | —                    | 0.596 / 0.091                      | 中等        | <sup>[\[67\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-67)[\[68\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-68)</sup>                                                                                                                         |
| BGE-base-en-v1.5             | 密集                  | 强大的通用嵌入器        | —                     | —                    | 0.781 / 0.141                      | 中等        | <sup>[\[69\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-69)</sup>                                                                                                                                                                                                                                                 |
| Cohere embed-english-v3.0    | 密集                  | 工业级文本嵌入模型      | —                     | —                    | 0.818 / 0.159                      | 中等        | <sup>[\[70\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-70)</sup>                                                                                                                                                                                                                                                 |
| BM25 + 密集 (示例: BM25+BGE) | 混合                  | 并行检索 + 列表融合     | RRF (k≈60) 或加权组合 | 可选: MonoT5/ColBERT | (因实现而异；通常优于单一最佳通道) | 中等        | <sup>[\[71\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-71)[\[72\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-72)[\[73\]](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_note-73)</sup> |

\`trec-covid\` 数据集上的方法比较

注：最后一行仅为方案示意；具体数值取决于嵌入模型的选择、归一化方法和融合参数（详见参考文献及 Pyserini 的可复现脚本）。

## 外部链接

- Pyserini / Anserini: <a href="https://github.com/castorini/pyserini" class="external text" rel="nofollow">github.com/castorini/pyserini</a> • <a href="https://github.com/castorini/anserini" class="external text" rel="nofollow">github.com/castorini/anserini</a>
- FAISS: <a href="https://arxiv.org/abs/1702.08734" class="external text" rel="nofollow">arXiv:1702.08734</a>
- Weaviate (Hybrid search): <a href="https://docs.weaviate.io/weaviate/search/hybrid" class="external text" rel="nofollow">docs.weaviate.io/weaviate/search/hybrid</a>
- pgvector: <a href="https://github.com/pgvector/pgvector" class="external text" rel="nofollow">github.com/pgvector/pgvector</a>
- Vespa (Hybrid search tutorial): <a href="https://docs.vespa.ai/en/tutorials/hybrid-search.html" class="external text" rel="nofollow">docs.vespa.ai/en/tutorials/hybrid-search.html</a>

## 参考文献

- Manning, C.D., Raghavan, P., Schütze, H. (2008). *Introduction to Information Retrieval*. Cambridge University Press. ISBN 978‑0521865715.
- Robertson, S., Zaragoza, H. (2009). *The Probabilistic Relevance Framework: BM25 and Beyond*. Foundations and Trends in Information Retrieval 3(4):333–389. DOI:10.1561/1500000019.
- Lin, J. et al. (2021). *Pyserini: A Python Toolkit for Reproducible IR*. SIGIR.
- Järvelin, K., Kekäläinen, J. (2002). *Cumulated Gain‑Based Evaluation of IR Techniques*. Information Retrieval 6:241–256. DOI:10.1023/A:1016043826386.
- Dean, J., Barroso, L.A. (2013). *The Tail at Scale*. CACM 56(2):74–80. DOI:10.1145/2408776.2408794.

## 注释

1.  <span id="cite_note-1">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-1) Robertson, S., Zaragoza, H. (2009). *The Probabilistic Relevance Framework: BM25 and Beyond*. Foundations and Trends in Information Retrieval, 3(4), 333–389. DOI:10.1561/1500000019.</span>
2.  <span id="cite_note-2">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-2) Cormack, G.V., Clarke, C.L.A., Büttcher, S. (2009). *Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods*. SIGIR 2009, 758–759. <a href="https://cormack.uwaterloo.ca/cormacksigir09-rrf.pdf" class="external text" rel="nofollow">PDF</a>.</span>
3.  <span id="cite_note-3">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-3) Bruch, S., Gai, S., Ingber, A. (2023). *An Analysis of Fusion Functions for Hybrid Retrieval*. ACM TOIS 42(1):1–35. DOI:10.1145/3596512 • arXiv:2210.11934.</span>
4.  <span id="cite_note-4">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-4) Manning, C.D., Raghavan, P., Schütze, H. (2008). *Introduction to Information Retrieval*. Cambridge University Press. ISBN 978‑0521865715 (см. главы о TF‑IDF, оценке и проблеме *vocabulary mismatch*).</span>
5.  <span id="cite_note-5">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-5) Izacard, G. et al. (2022). *Unsupervised Dense Information Retrieval with Contrastive Learning (Contriever)*. TACL 10:1089–1108. arXiv:2112.09118.</span>
6.  <span id="cite_note-6">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-6) Wang, L. et al. (2022/2024). *Text Embeddings by Weakly‑Supervised Contrastive Pre‑training (E5)*. arXiv:2212.03533.</span>
7.  <span id="cite_note-7">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-7) Robertson, S., Zaragoza, H. (2009). *The Probabilistic Relevance Framework: BM25 and Beyond*. DOI:10.1561/1500000019.</span>
8.  <span id="cite_note-8">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-8) Formal, T., Piwowarski, B., Clinchant, S. (2021). *SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking*. arXiv:2107.05720.</span>
9.  <span id="cite_note-9">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-9) Formal, T. et al. (2022). *Making Sparse Neural IR Models More Effective*. Findings of EMNLP. arXiv:2205.04733.</span>
10. <span id="cite_note-10">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-10) Formal, T. et al. (2024). *SPLADE‑v3: New baselines for SPLADE*. arXiv:2403.06789.</span>
11. <span id="cite_note-11">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-11) Lin, J., Ma, X. (2021). *A Few Brief Notes on DeepImpact, COIL, and uniCOIL*. arXiv:2106.14807.</span>
12. <span id="cite_note-12">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-12) Karpukhin, V. et al. (2020). *Dense Passage Retrieval for Open‑Domain QA*. EMNLP. arXiv:2004.04906.</span>
13. <span id="cite_note-13">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-13) Xiong, L. et al. (2021). *Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval (ANCE)*. ICLR. arXiv:2007.00808.</span>
14. <span id="cite_note-14">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-14) Izacard, G. et al. (2022). TACL. arXiv:2112.09118.</span>
15. <span id="cite_note-15">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-15) Ni, J. et al. (2021/2022). *Large Dual Encoders Are Generalizable Retrievers (GTR)*. EMNLP. arXiv:2112.07899.</span>
16. <span id="cite_note-16">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-16) Wang, L. et al. (2022/2024). arXiv:2212.03533.</span>
17. <span id="cite_note-17">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-17) Khattab, O., Zaharia, M. (2020). *ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT*. SIGIR. arXiv:2004.12832.</span>
18. <span id="cite_note-18">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-18) Santhanam, K. et al. (2022). *ColBERTv2 & PLAID*. NAACL/ArXiv. arXiv:2112.01488; arXiv:2205.09707.</span>
19. <span id="cite_note-19">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-19) Scheerer, J.L. et al. (2025). *WARP: An Efficient Engine for Multi‑Vector Retrieval*. arXiv:2501.17788.</span>
20. <span id="cite_note-20">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-20) Lin, J. et al. (2021). *Pyserini: A Python Toolkit for Reproducible IR with Sparse and Dense Representations*. SIGIR. <a href="https://cs.uwaterloo.ca/~jimmylin/publications/Lin_etal_SIGIR2021_Pyserini.pdf" class="external text" rel="nofollow">PDF</a>.</span>
21. <span id="cite_note-21">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-21) Cormack, G.V., Clarke, C.L.A., Büttcher, S. (2009). SIGIR. <a href="https://cormack.uwaterloo.ca/cormacksigir09-rrf.pdf" class="external text" rel="nofollow">PDF</a>.</span>
22. <span id="cite_note-22">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-22) Elastic Docs. *Reciprocal Rank Fusion*. (доступ 2025‑09‑10). <a href="https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion" class="external text" rel="nofollow">elastic.co/docs/.../reciprocal-rank-fusion</a>.</span>
23. <span id="cite_note-23">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-23) OpenSearch Docs. *Score ranker processor (RRF)*. (доступ 2025‑09‑10). <a href="https://docs.opensearch.org/3.0/search-plugins/search-pipelines/score-ranker-processor/" class="external text" rel="nofollow">docs.opensearch.org/.../score-ranker-processor/</a>.</span>
24. <span id="cite_note-24">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-24) Fox, E.A., Shaw, J.A. (1994). *Combination of Multiple Searches*. TREC‑2, NIST SP 500‑215, 243–252. <a href="https://www.khoury.northeastern.edu/home/jaa/CSG339.06F/resources/fox94combination.pdf" class="external text" rel="nofollow">PDF</a>.</span>
25. <span id="cite_note-25">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-25) Lee, J.H. (1997). *Analyses of Multiple Evidence Combination*. SIGIR, 267–276. DOI:10.1145/258525.258587.</span>
26. <span id="cite_note-26">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-26) Hsu, D.F., Taksa, I. (2005). *Comparing Rank and Score Combination Methods for Data Fusion in IR*. (Tech. report). <a href="https://ccc.inaoep.mx/~villasen/bib/Hsu-FusionInIR07.pdf" class="external text" rel="nofollow">PDF</a>.</span>
27. <span id="cite_note-27">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-27) Bruch, S., Gai, S., Ingber, A. (2023). TOIS. DOI:10.1145/3596512.</span>
28. <span id="cite_note-28">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-28) Hsu, D.F., Taksa, I. (2005). см. выше.</span>
29. <span id="cite_note-29">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-29) Bruch, S., Gai, S., Ingber, A. (2023). TOIS. DOI:10.1145/3596512.</span>
30. <span id="cite_note-30">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-30) Nogueira, R., Cho, K. (2019). *Passage Re‑ranking with BERT*. arXiv:1901.04085.</span>
31. <span id="cite_note-31">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-31) Nogueira, R., Jiang, Z., Lin, J. (2020). *Document Ranking with a Pretrained Sequence‑to‑Sequence Model (MonoT5)*. Findings of EMNLP. arXiv:2003.06713.</span>
32. <span id="cite_note-32">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-32) Santhanam, K. et al. (2022). arXiv:2205.09707.</span>
33. <span id="cite_note-33">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-33) Scheerer, J.L. et al. (2025). arXiv:2501.17788.</span>
34. <span id="cite_note-34">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-34) Dean, J., Barroso, L.A. (2013). *The Tail at Scale*. CACM 56(2):74–80. DOI:10.1145/2408776.2408794.</span>
35. <span id="cite_note-35">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-35) Thakur, N. et al. (2021). *BEIR: A Heterogeneous Benchmark for Zero‑shot Evaluation of IR Models*. NeurIPS Datasets & Benchmarks. arXiv:2104.08663.</span>
36. <span id="cite_note-36">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-36) Craswell, N. et al. (2020). *Overview of the TREC 2019 Deep Learning Track*. arXiv:2003.07820.</span>
37. <span id="cite_note-37">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-37) Craswell, N. et al. (2021). *Overview of the TREC 2020 Deep Learning Track*. arXiv:2102.07662.</span>
38. <span id="cite_note-38">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-38) Bajaj, P. et al. (2016). *MS MARCO: A Human Generated MAchine Reading COmprehension Dataset*. arXiv:1611.09268.</span>
39. <span id="cite_note-39">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-39) Järvelin, K., Kekäläinen, J. (2002). *Cumulated Gain‑Based Evaluation of IR Techniques*. Information Retrieval 6:241–256. DOI:10.1023/A:1016043826386.</span>
40. <span id="cite_note-40">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-40) Dean, J., Barroso, L.A. (2013). CACM. DOI:10.1145/2408776.2408794.</span>
41. <span id="cite_note-41">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-41) Bruch, S. et al. (2023). DOI:10.1145/3596512.</span>
42. <span id="cite_note-42">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-42) Ni, J. et al. (2021/2022). arXiv:2112.07899.</span>
43. <span id="cite_note-43">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-43) Johnson, J., Douze, M., Jégou, H. (2017). *Billion‑scale Similarity Search with GPUs (FAISS)*. arXiv:1702.08734.</span>
44. <span id="cite_note-44">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-44) Malkov, Y., Yashunin, D. (2020). *HNSW*. IEEE TPAMI 42(4):824–836. DOI:10.1109/TPAMI.2018.2889473.</span>
45. <span id="cite_note-45">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-45) Guo, R. et al. (2020). *ScaNN: Efficient Vector Similarity Search at Scale*. arXiv:1908.10396.</span>
46. <span id="cite_note-46">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-46) Yang, P., Fang, H., Lin, J. (2018). *Anserini: Reproducible IR Research with Lucene*. JDIQ 10(4):1–20. DOI:10.1145/3239571.</span>
47. <span id="cite_note-47">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-47) Lin, J. et al. (2021). SIGIR. <a href="https://cs.uwaterloo.ca/~jimmylin/publications/Lin_etal_SIGIR2021_Pyserini.pdf" class="external text" rel="nofollow">PDF</a>.</span>
48. <span id="cite_note-48">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-48) Qdrant Docs. *Hybrid queries (RRF, DBSF)*. (доступ 2025‑09‑10). <a href="https://qdrant.tech/documentation/concepts/hybrid-queries/" class="external text" rel="nofollow">qdrant.tech/.../hybrid-queries/</a>.</span>
49. <span id="cite_note-49">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-49) Weaviate Docs. *Hybrid search*. (доступ 2025‑09‑10). <a href="https://docs.weaviate.io/weaviate/search/hybrid" class="external text" rel="nofollow">docs.weaviate.io/weaviate/search/hybrid</a>.</span>
50. <span id="cite_note-50">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-50) pgvector GitHub. (доступ 2025‑09‑10). <a href="https://github.com/pgvector/pgvector" class="external text" rel="nofollow">github.com/pgvector/pgvector</a>.</span>
51. <span id="cite_note-51">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-51) Vespa Docs. *Hybrid Text Search Tutorial*. (доступ 2025‑09‑10). <a href="https://docs.vespa.ai/en/tutorials/hybrid-search.html" class="external text" rel="nofollow">docs.vespa.ai/.../hybrid-search.html</a>.</span>
52. <span id="cite_note-52">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-52) Elastic Docs. *Reciprocal Rank Fusion*. (доступ 2025‑09‑10). <a href="https://www.elastic.co/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion" class="external text" rel="nofollow">elastic.co/docs/.../rrf</a>.</span>
53. <span id="cite_note-53">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-53) Lewis, P. et al. (2020). *Retrieval‑Augmented Generation for Knowledge‑Intensive NLP Tasks*. NeurIPS. arXiv:2005.11401.</span>
54. <span id="cite_note-54">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-54) Hsu, D.F., Taksa, I. (2005). см. выше.</span>
55. <span id="cite_note-55">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-55) Ni, J. et al. (2021/2022). arXiv:2112.07899.</span>
56. <span id="cite_note-56">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-56) Formal, T. et al. (2021, 2022, 2024). arXiv:2107.05720; 2205.04733; 2403.06789.</span>
57. <span id="cite_note-57">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-57) Lewis, P. et al. (2020). arXiv:2005.11401.</span>
58. <span id="cite_note-58">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-58) Gao, L. et al. (2023). *Precise Zero‑Shot Dense Retrieval without Relevance Labels (HyDE)*. ACL. arXiv:2212.10496.</span>
59. <span id="cite_note-59">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-59) Nogueira, R. et al. (2019). *Document Expansion by Query Prediction*. arXiv:1904.08375; *docTTTTTquery*. <a href="https://cs.uwaterloo.ca/~jimmylin/publications/Nogueira_Lin_2019_docTTTTTquery-v2.pdf" class="external text" rel="nofollow">PDF</a>.</span>
60. <span id="cite_note-60">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-60) Santhanam, K. et al. (2022). arXiv:2205.09707.</span>
61. <span id="cite_note-61">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-61) Scheerer, J.L. et al. (2025). arXiv:2501.17788.</span>
62. <span id="cite_note-62">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-62) Pyserini *BEIR Regressions* (доступ 2025‑09‑10): результаты по *trec‑covid* для BM25/SPLADE/Contriever/BGE/Cohere. <a href="https://castorini.github.io/pyserini/2cr/beir.html" class="external text" rel="nofollow">castorini.github.io/pyserini/2cr/beir.html</a>.</span>
63. <span id="cite_note-63">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-63) Robertson, S., Zaragoza, H. (2009). DOI:10.1561/1500000019.</span>
64. <span id="cite_note-64">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-64) Pyserini BEIR. См. ссылку выше.</span>
65. <span id="cite_note-65">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-65) Formal, T. et al. (2021, 2022). arXiv:2107.05720; 2205.04733.</span>
66. <span id="cite_note-66">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-66) Pyserini BEIR.</span>
67. <span id="cite_note-67">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-67) Izacard, G. et al. (2022). arXiv:2112.09118.</span>
68. <span id="cite_note-68">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-68) Pyserini BEIR.</span>
69. <span id="cite_note-69">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-69) Pyserini BEIR.</span>
70. <span id="cite_note-70">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-70) Pyserini BEIR.</span>
71. <span id="cite_note-71">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-71) Cormack et al. (2009). SIGIR. RRF.</span>
72. <span id="cite_note-72">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-72) Bruch et al. (2023). TOIS.</span>
73. <span id="cite_note-73">[↑](https://systems-analysis.info/int/Hybrid_retrieval_%E2%80%94_%E6%B7%B7%E5%90%88%E6%A3%80%E7%B4%A2#cite_ref-73) Elastic/OpenSearch RRF Docs.</span>