index construction

This work addresses the lack of systematic design principles for neural retrieval systems that balance efficiency and effectiveness. It proposes the first vertically layered four-tier framework—spanning representation, granularity, orchestration, and robustness—to structurally characterize key design decisions at each layer and their interdependencies. By integrating Bi- and Cross-encoder architectures, atomic and hierarchical chunking strategies, multi-stage re-ranking, agent-based decomposition, and domain generalization techniques, the study elucidates the mechanistic impact of each design choice on system performance. This approach effectively mitigates critical challenges such as information bottlenecks, semantic blind spots, and temporal drift, thereby offering a practical and actionable optimization pathway for building efficient and robust embedded retrieval systems.

This work addresses the challenge of deploying a shared retrieval backbone in industrial systems, where balancing performance and deployment flexibility across multiple downstream tasks remains difficult. To overcome the limitations of conventional approaches that rely on a single optimal checkpoint, the authors propose a multi-stage optimization framework that tailors component-level and hybrid-stage configuration strategies to the distinct performance characteristics of dense retrievers and rerankers throughout training. This approach significantly enhances the adaptability of the shared backbone and improves overall retrieval effectiveness. End-to-end evaluation demonstrates that the resulting shared retrieval service has been successfully deployed across multiple industrial applications, delivering substantial gains in both system performance and scalability.

This work addresses the lack of conceptually structured corpus partitioning in existing large-scale Retrieval-Augmented Generation (RAG) systems, which leads to uncontrollable and uninterpretable retrieval processes. To remedy this, the study introduces, for the first time, OLAP-style multidimensional modeling into RAG architecture by proposing a Dimensional Fact Model (DFM) as a conceptual framework for corpus organization. By integrating semantic clustering with multidimensional partitioning strategies, the approach enables hierarchical routing and a controllable fallback mechanism. Leveraging metadata-driven retrieval control, the authors construct an interpretable and governable large-scale retrieval prototype system, thereby establishing principled design guidelines and a practical pathway for structured corpus partitioning in industrial-grade RAG deployments.

In multi-vector databases, systematic index tuning methodologies are lacking for multimodal or multi-feature scenarios, leading to high query latency and suboptimal trade-offs among storage cost, recall, and efficiency. Method: This paper formally defines the multi-vector search index tuning problem and proposes a holistic framework that jointly optimizes query latency, storage overhead, and recall—departing from conventional single-vector or relational indexing paradigms. It introduces a workload-driven search space pruning algorithm, a multi-objective constrained modeling mechanism, and an efficient index evaluator. Contribution/Results: Evaluated on real-world multi-vector workloads, our approach reduces query latency by 2.1×–8.3× over state-of-the-art baselines while satisfying user-specified storage and recall constraints. It identifies Pareto-optimal index configurations, enabling principled, workload-aware index selection in multi-vector settings.

Existing hybrid search systems lack systematic empirical analysis of trade-offs among lexical and semantic retrieval components—i.e., retrieval paradigms, fusion strategies, and re-ranking methods—leading to complex, suboptimal configurations. Method: We introduce the first benchmark framework tailored for advanced hybrid architectures, conducting systematic evaluation across 11 real-world datasets, covering four retrieval paradigms, their combinations, and re-ranking strategies. Contribution/Results: We identify a “weakest-link” effect in hybrid pipelines and propose a data-driven configuration mapping method. Crucially, we find Tensor-based Re-ranking Fusion (TRF) achieves both high efficiency and strong semantic modeling under low-resource conditions, overcoming traditional fusion bottlenecks. Experiments reveal that hybrid performance is severely constrained by imbalanced path quality; optimal configurations are highly dependent on dataset characteristics and resource constraints. TRF significantly improves the effectiveness–cost trade-off, outperforming state-of-the-art baselines across diverse settings.

To address challenges in dynamic system integration—including difficulty in API endpoint discovery and high token overhead in retrieval-augmented generation (RAG)—this paper proposes a summary-based Discovery Agent architecture. First, OpenAPI specifications are processed via format-aware, LLM-driven intelligent chunking to generate semantically compact endpoint summaries. Second, an efficient retrieval pipeline combines summary-based pre-filtering with on-demand loading of fine-grained details. This work presents the first systematic evaluation of OpenAPI chunking strategies for RAG-based endpoint discovery. On the RestBench benchmark, our method significantly improves F1 score (+12.3%) and precision (+15.6%) over naive chunking, maintains high recall (92.4%), and reduces token consumption by 68%. Key contributions include: (1) a format-aware chunking paradigm for OpenAPI documents; (2) an endpoint-level summary pre-filtering mechanism; and (3) a lightweight, efficient RAG framework tailored for API endpoint discovery.

This work addresses the challenge of expansion bias in large-scale retrieval systems, which disproportionately affects fresh and long-tail content, leading to uneven model performance gains. To mitigate this, the authors propose MESH, a unified retrieval expansion framework that incorporates structural inductive biases through a modular neural architecture, feature space partitioning, and a gated bias-correction mechanism. This design preserves gradient pathways for sparse items, effectively decoupling interference between high-frequency and sparse signals while enabling asynchronous inference to enhance throughput. Evaluated on Pinterest’s billion-scale recommendation system, MESH achieves a 5.5% increase in re-pin rate for fresh content, a 55% improvement in funnel efficiency, a 0.46% gain in user retention, and a 2.87× boost in system throughput.

This work addresses the challenge of balancing fine-grained semantic representation and retrieval efficiency in multi-vector retrieval, which has been hindered by the absence of efficient indexing mechanisms. To this end, we propose GEM, a native graph-based indexing framework that, for the first time, designs an index structure specifically for sets of vectors. GEM integrates set-level clustering, local proximity graph connectivity, and global navigation, while decoupling graph construction metrics from relevance scoring. It further introduces semantic shortcuts and a multi-entry beam search mechanism, enhanced with quantized distance estimation, to significantly accelerate retrieval. Experimental results demonstrate that GEM achieves up to a 16× speedup over existing methods across multiple benchmarks, while maintaining or even improving retrieval accuracy.

This study investigates whether retrieval fusion techniques—commonly adopted in real-world retrieval-augmented generation (RAG) systems, such as multi-query retrieval and reciprocal rank fusion—consistently improve end-to-end answer quality under practical deployment constraints. Conducted within an enterprise knowledge-base RAG pipeline, the evaluation is performed under fixed retrieval depth, reranking budget, and latency limits. While retrieval fusion enhances initial recall, it fails to translate into improved Top-k accuracy after subsequent reranking and context truncation; notably, Hit@10 declines from 0.51 to 0.48 and incurs additional latency. These findings challenge the prevailing assumption of the default efficacy of recall-oriented fusion strategies, revealing diminishing returns in production settings where downstream processing and system constraints critically shape overall performance.

Current retrieval-augmented generation systems require uploading sensitive documents to remote servers, posing significant privacy risks. This work proposes a “local-first information retrieval” paradigm that fully deploys indexing, models, and inference on the user’s device, with optional remote service invocation. The authors formally define this design paradigm for the first time and establish a system framework centered on three dimensions: privacy control, capability, and accessibility. They identify search scope—not quality—as the primary trade-off in local-first systems. Experimental results demonstrate that, on consumer-grade hardware, a local system combining dense retrieval, BM25, and HNSW indexing achieves over 91% nDCG@10 on collections of up to 100K documents, with only a 2% drop when scaled to 1M documents. Furthermore, question-answering quality using a 7B-parameter language model lags behind cloud-based baselines by merely 4 points.

This work addresses the architectural challenges faced by industrial-scale web retrieval systems under stringent constraints of latency, scalability, and resource efficiency. It proposes a unified multi-stage abstraction termed “Retrieval-as-a-Service” (RaaS), which, for the first time, integrates infrastructure-aware components—including efficient candidate generation, embedding-based semantic matching, and resource-conscious re-ranking—into a cohesive framework. The study systematically models the impact of incorporating large language models (LLMs) on both system performance and operational overhead. By analyzing real-world production deployments, the authors uncover fundamental trade-offs between system design choices and quality-of-service (QoS) objectives, thereby offering practical, scalable, and QoS-aware architectural guidelines for building high-performance web-scale retrieval systems.