retrieval-augmented candidate generation

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.

In information retrieval (IR) experiments, pipeline-based architectures suffer from redundant computation—e.g., repeated retrieval for multi-ranker comparisons—and design–implementation misalignment due to reliance on intermediate result files. To address these issues, this paper proposes a dual-path caching mechanism. First, we introduce *implicit prefix caching*, a novel technique that automatically identifies and reuses common subcomputations via runtime cache-key derivation and operation-sequence hashing. Second, we design *pyterrier-caching*, a pluggable explicit caching extension supporting persistent storage of intermediate representations and modular integration. Implemented atop PyTerrier, our approach preserves end-to-end semantic integrity while significantly reducing I/O overhead and retrieval latency. Empirical evaluation across realistic IR research workflows demonstrates the method’s effectiveness, generality across diverse experimental configurations, and ease of adoption—requiring minimal code changes and no modification to existing pipelines.

This work addresses the inefficiency in end-to-end evaluation of cascaded information retrieval (IR) pipelines caused by redundant computation. It introduces, for the first time, the Trie data structure into IR experimental design to automatically identify and reuse shared sub-pipelines, thereby constructing highly efficient comparative evaluation plans. Implemented within the PyTerrier framework, the approach supports combined evaluation of diverse models, including BM25, MonoT5, and DuoT5. Experiments on the MSMARCO v2 dataset demonstrate a 26% reduction in runtime compared to conventional linear evaluation plans, while user studies confirm the method’s usability and practical utility for IR researchers.

This study addresses the challenge of inefficient cross-site and cross-organizational reuse of industrial spare parts, hindered by decentralized storage, inconsistent naming conventions, and missing information. To overcome these issues, the authors propose PhRAG, a novel framework that integrates multitask generative language modeling with named entity recognition and hybrid retrieval-augmented generation (RAG) to construct a unified virtual spare parts pool (VSPool) from heterogeneous unstructured data. The approach achieves robust structured information extraction under data-scarce conditions and enables natural language querying with generative, interpretable retrieval. Experimental results demonstrate that PhRAG outperforms conventional NER methods in technical specification extraction and significantly enhances both the efficiency of spare parts reuse across organizations and the transparency of the overall system.

This work addresses the challenge of efficient skill selection and ranking from large skill repositories, where full loading incurs high costs and existing systems lack autonomous scheduling mechanisms. The authors compare two retrieval approaches: a hybrid ranker combining lexical and dense embeddings that enables on-demand sparse loading, and a typed workflow knowledge graph encoding preconditions and dataflow dependencies. Experimental results show that augmenting the strong ranker with graph structure does not improve retrieval effectiveness—graph candidates are confined to the embedding neighborhood already covered by the ranker, limiting scope expansion. On 117 real-world queries, the hybrid ranker achieves a Top-5 hit rate of 73.5% ± 8.0%, whereas the knowledge graph underperforms by 11.2 points (p = 0.0007) under the same token budget and fails to recover 73% of queries missed by the ranker. The study also reveals that self-authored queries can overestimate hit rates by up to 44 percentage points, exposing significant evaluation bias.

This work addresses the challenge of retrieval and routing errors in large-scale skill repositories, where semantically similar skills often exhibit insufficient textual distinction. To mitigate this, the authors propose Capability Pages—a structured representation that formalizes a skill’s capability as its executable region through offline compilation, yielding a contrastive encoding comprising positive triggers, negative boundaries, and discriminative anchors. Notably, negative boundaries are explicitly introduced to model mutual exclusivity among skills, effectively reducing ambiguity-induced retrieval errors without requiring modifications to online models. The approach integrates clustering-based contrastive learning, a two-stage retrieval pipeline (recall followed by rejection), and cross-lingual transfer. Evaluated on SRA-Bench, it achieves a 2.94-point gain in Recall@10 and a 3.62-point improvement in end-to-end task success rate; on the Chinese SSL-SkillDiscovery benchmark, it attains an MRR@50 of 73.07%.

This study addresses the challenge of fragmented qualification data for electronic components in aerospace engineering, which is scattered across multiple heterogeneous systems and impedes efficient decision-making during design phases. To overcome this, the authors propose a semantic integration approach that synergistically combines virtual knowledge graphs with large language models. By leveraging an ontology-based data access (OBDA) framework alongside vector retrieval mechanisms, the method enables unified and efficient querying of qualification information across disparate data silos. The approach maintains strong semantic consistency while substantially reducing manual data curation costs. Compared to conventional retrieval-augmented generation (RAG) or pure large-model solutions, it demonstrates superior performance in retrieval accuracy, computational efficiency, and long-term operational cost, thereby effectively minimizing redundant certification efforts.