DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking

Litong Zhang; Jiaxin Li; Kuo Zhao

cs.IRApr 13, 2026

DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking

Authors: Litong Zhang, Jiaxin Li, Kuo Zhao

Organizations: Jinan University, Guangzhou, Guangdong, China

Abstract

Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental challenge lies in efficiently identifying the minimal relevant document set from retrieved candidates while maintaining high recall. We present an efficient dual-view cascaded reranking framework for multi-hop document reranking. Operating as a lightweight post-retrieval stage over E5-base-v2 candidates, our architecture comprises: (1) a Local Scorer employing stacked cross-attention for fine-grained query-document relevance; and (2) a Global Scorer modeling inter-document dependencies via Transformer-based context aggregation. These views are dynamically fused through an Adaptive Gate conditioned on query semantics. Under the fixed candidate set reranking setting with offline cached embeddings, our model achieves competitive results, particularly outstanding on MuSiQue with 99.4% Top-4 Recall and 97.8% Full Hit accuracy at 4.0 ms latency (249 QPS). It substantially outperforms 600M-parameter cross-encoders (BGE-Large: 92.0% Recall, Jina-v3: 90.1% Recall) while maintaining 5 to 6 times lower latency. Ablation studies validate that both Local and Global views contribute substantially to multi-hop performance.

Figures & tables

Figure 1. Overview of our lightweight cascaded reranker. Given a query and candidate documents encoded by a frozen E5 encoder, the Local Scorer captures fine-grained query-document interactions, the Global Scorer models inter-document contextual relationships through a 2-layer Transformer, and the Adaptive Gate dynamically fuses both views conditioned on query semantics. Architecture diagram showing the three-stage pipeline: (1) Frozen E5 encoder produces 768-dim embeddings for query and documents; (2) Local Scorer applies stacked cross-attention to compute query-document relevance; (3) Global Scorer processes the document set via induced set attention to capture context; (4) Adaptive Gate fuses local and global scores with query-conditioned weighting. The final output is a reranked document list for downstream LLM generation.

Figure 2. Architecture of the Local and Global Scorers. The frozen E5 encoder produces embeddings for both query and documents. The Local Scorer (left) applies stacked cross-attention to capture fine-grained query-document interactions, while the Global Scorer (right) employs Transformer-based context aggregation over local features to model inter-document dependencies. Architecture diagram showing Local Scorer with cross-attention layers and Global Scorer with Transformer-based aggregation.

Figure 3. Adaptive Gate architecture for dynamic view fusion. The gate receives local features, global features, and query embedding as inputs. Through query-conditioned projections, it computes a fusion weight $g_{i}$ for each document to dynamically balance local and global scores based on query semantics. Adaptive Gate architecture showing projection layers and query-conditioned fusion mechanism.

Dataset	Split	Samples	Candidates
2WikiMultihopQA ( Ho et al., 2020 )	Train	7,500 (50%)	10
2WikiMultihopQA	Dev	7,785	10
HotpotQA ( Yang et al., 2018 )	Train	10,000 (11.1%)	10
HotpotQA	Dev	7,405	10
MuSiQue ( Trivedi et al., 2022 )	Train	9,969 (50%)	6
MuSiQue	Dev	2,417	6

Table 1. Dataset statistics. All candidate sets are pre-constructed with fixed size limits and pre-computed E5 embeddings.

Model	Params	R@4	FH@4	N@4	M@4	P@4
E5-Cosine	0M	83.5	62.8	84.6	97.5	49.1
E5-MLP	0.6M	94.2	86.0	92.2	96.0	57.4
Ours	11M	93.9	85.0	92.8	97.4	57.1
MiniLM-L6	22M	78.6	54.2	81.0	97.8	45.9
BGE-Large	560M	87.8	69.6	89.4	99.8	52.2
BGE-v2-m3	568M	86.5	67.1	88.1	99.6	51.3

Table 2. Retrieval performance on 2WikiMultihopQA (in-domain, Top-4). Bold : best overall; underlined : best

\leq

22M params.

Model	Params	R@4	FH@4	N@4	M@4	P@4
E5-Cosine	0M	89.0	78.8	86.6	94.0	44.6
E5-MLP	0.6M	88.2	77.7	83.9	89.9	44.2
Ours	11M	90.8	82.5	87.8	93.6	45.6
MiniLM-L6	22M	83.4	67.8	83.0	95.0	41.9
BGE-Large	560M	95.8	91.9	94.6	98.1	48.1
BGE-v2-m3	568M	95.3	90.9	93.9	97.9	47.8

Table 3. Retrieval performance on HotpotQA (held-out dev set, Top-4).

Model	Params	R@4	FH@4	N@4	M@4	P@4
E5-Cosine	0M	71.9	38.3	67.2	83.2	44.9
E5-MLP	0.6M	98.4	94.7	97.8	99.6	64.9
Ours	11M	99.4	97.8	99.2	99.9	65.7
MiniLM-L6	22M	77.3	48.0	78.5	94.9	49.8
BGE-Large	560M	92.0	78.1	90.9	97.6	59.7
BGE-v2-m3	568M	89.4	71.4	88.7	97.2	57.9

Table 4. Retrieval performance on MuSiQue (held-out dev set, most challenging, Top-4). Our 11M model achieves SOTA with 54

\times

fewer parameters than cross-encoders.

Model	Params	Mean (ms)	P95 (ms)	QPS	Type
E5-Cosine	0M	3.1	3.2	327	bi-encoder
E5-MLP	0.6M	3.3	3.6	303	MLP reranker
Ours	11M	4.0	4.1	249	cascaded
MiniLM-L6	22M	3.7	6.2	271	cross-encoder
BGE-Large	560M	21.8	36.8	46	cross-encoder
BGE-v2-m3	568M	21.9	37.6	46	cross-encoder

Table 5. Inference efficiency (online, doc embeddings cached). Lower latency and higher QPS are better. All measurements on NVIDIA RTX 4090, batch size 1.

Configuration	R@4	FH@4	N@4	M@4	P@4
Full-Model (Ours)	99.4	97.8	99.2	99.9	65.7
$-$ Adaptive Gate (avg fusion)	96.1	87.7	95.2	99.0	63.0
$-$ Global Scorer	95.9	87.1	94.9	98.9	62.9
$-$ Local Scorer (global-only)	84.0	61.1	79.3	87.8	53.7
E5-MLP (0.6M baseline)	98.4	94.7	97.8	99.6	64.9

Table 6. Ablation study on MuSiQue development set (Top-4 metrics). MuSiQue’s 2–4 hop complexity better reveals component contributions for multi-hop reasoning.

Multi-Hop QA

Multi-hop question answering studies how systems combine evidence across documents, facts, or modalities to answer questions requiring linked reasoning.

See all 221 papers

A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
Oct 1, 2026Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5Multi-Hop QA Retrieval-Augmented Generation
Polytechnic University of Marche, Ancona, Italy · University of Modena and Reggio Emilia, Modena, Italy
Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
Sep 7, 2026JungMin Yun, YoungBin KimEvidence Retrieval Information Retrieval
Chung-Ang University Seoul, Republic of Korea
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
Sep 17, 2026Lijun Liu, Zhengzong Chen, Wenyan Li +2Learning to Rank RL for Language Model Reasoning
Honor Device Co., Ltd

Oct 1, 2026J/K move · Enter open · S save

A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering

Gianluca Bonifazi, Christopher Buratti, Michele Marchetti, Federica Parlapiano+4

Polytechnic University of Marche, Ancona, Italy · University of Modena and Reggio Emilia, Modena, Italy

Multi-Hop QA Retrieval-Augmented Generation

Open paper AskPDF arXiv

Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing time, through the use of expensive Knowledge Graphs (KGs) or Large Language Models (LLMs) to generate summaries, or during querying, through iterative LLM-driven retrieval. To reduce it while maintaining retrieval quality, we present MatRAG, a hierarchical framework that combines RAG systems with Matryoshka Representation Learning (MRL). MatRAG addresses both kinds of cost by aligning the semantic hierarchy of a clustering structure with the nested structure of MRL. Specifically, it organizes the corpus of documents into a Directed Acyclic Graph (DAG) of clusters with progressively coarser granularity. Each level is indexed by a lower Matryoshka dimension. MatRAG pairs an iterative, top-down traversal of the DAG with an entity-driven mechanism that controls the hop budget and re-ranks candidates. We evaluated MatRAG on three standard multi-hop QA benchmarks against seven representative baselines. MatRAG outperforms its strongest competitors in terms of retrieval quality; furthermore, it reduces indexing costs by avoiding KG construction and LLM-based summarization, and lowers query-time costs through dimension-aware similarity.

Abstract

Multi-Hop QA

Explore similar work

A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval

Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking