KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs

• URL: http://arxiv.org/abs/2511.18364v1
• Date: Sun, 23 Nov 2025 09:21:14 GMT
• Title: KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs
• Abstract summary: Building high-quality knowledge graphs (KGs) from diverse sources requires combining methods for information extraction, data transformation, ontology mapping, entity matching, and data fusion.<n>We present a new framework, KGpipe for defining and executing pipelines that can combine existing tools or LLM (Large Language Model) functionality.
• Score: 1.5397834466394758
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Building high-quality knowledge graphs (KGs) from diverse sources requires combining methods for information extraction, data transformation, ontology mapping, entity matching, and data fusion. Numerous methods and tools exist for each of these tasks, but support for combining them into reproducible and effective end-to-end pipelines is still lacking. We present a new framework, KGpipe for defining and executing integration pipelines that can combine existing tools or LLM (Large Language Model) functionality. To evaluate different pipelines and the resulting KGs, we propose a benchmark to integrate heterogeneous data of different formats (RDF, JSON, text) into a seed KG. We demonstrate the flexibility of KGpipe by running and comparatively evaluating several pipelines integrating sources of the same or different formats using selected performance and quality metrics.

Related papers

• Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines [1.4180331276028662]
  Retrieval-augmented generation (RAG) systems have traditionally relied on text-based pipelines that extract and retrieve information from documents.<n>Recent advances in multimodal pipelines, powered by vision-language models (VLMs), improve retrieval quality by jointly encoding visual and textual signals, but at increased computational and memory cost.<n>We evaluate contemporary textual and multimodal pipelines, including dense and late-interaction architectures, analyze their trade-offs, and provide actionable guidance for balancing retrieval performance with system efficiency.
  arXiv  Detail & Related papers  (2026-08-24T12:25:52Z)
• Evaluation of Pipelines for Data Integration into Knowledge Graphs [1.5397834466394758]
  We propose a new benchmark KGI-Bench to evaluate integration pipelines that ingest different kinds of input data into an existing KG.<n>We evaluate pipelines by analyzing their output, with the three complementary quality metrics coverage, correctness and consistency.<n>We comparatively evaluate 12 pipelines and analyze their behavior across different input data formats and design choices.
  arXiv  Detail & Related papers  (2026-05-21T10:52:48Z)
• GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling [48.71974949983576]
  We present GenesisFunc, an automated pipeline for generating function-calling data.<n>Our method demonstrates strong potential to scale effectively across downstream tools, underscoring its real-world applicability.
  arXiv  Detail & Related papers  (2026-04-10T14:02:03Z)
• Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learning [8.071711833525475]
  Two crucial meta-learning tasks are pipeline performance estimation (PPE) and dataset performance-based similarity estimation (DPSE)<n>Existing approaches primarily rely on dataset meta-features to represent datasets numerically and approximate these meta-learning tasks.<n>We propose KGmetaSP, a knowledge-graph-embeddings approach that leverages existing experiment data to capture these interactions and improve both PPE and DPSE.
  arXiv  Detail & Related papers  (2026-03-20T11:57:25Z)
• Automatic End-to-End Data Integration using Large Language Models [3.188426002064626]
  We present an automatic data integration pipeline that uses GPT-5.2 to generate all artifacts required to adapt the pipeline to specific use cases.<n>We compare the performance of this LLM-based pipeline to the performance of human-designed pipelines along three case studies.<n>Our experiments show that the LLM-based pipeline is able to produce similar results, for some tasks even better results, as the human-designed pipelines.
  arXiv  Detail & Related papers  (2026-03-11T08:56:55Z)
• Nimbus: A Unified Embodied Synthetic Data Generation Framework [51.55989844555466]
  Scaling data volume and diversity is critical for generalizing embodied intelligence.<n>We present Nimbus, a unified synthetic data generation framework designed to integrate heterogeneous navigation and manipulation pipelines.<n>Our evaluation demonstrates that Nimbus achieves a 2-3X improvement in end-to-end throughput compared to unoptimized baselines.
  arXiv  Detail & Related papers  (2026-01-29T09:27:31Z)
• Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? [57.28763506780752]
  GraphFlow is a framework that efficiently retrieves accurate and diverse knowledge required for real-world queries from text-rich KGs.<n>It outperforms strong KG-RAG baselines, including GPT-4o, by 10% on average in hit rate and recall.<n>It also shows strong generalization to unseen KGs, demonstrating its effectiveness and robustness.
  arXiv  Detail & Related papers  (2025-10-18T17:06:49Z)
• MSRS: Evaluating Multi-Source Retrieval-Augmented Generation [51.717139132190574]
  Many real-world applications demand the ability to integrate and summarize information scattered across multiple sources.<n>We present a scalable framework for constructing evaluation benchmarks that challenge RAG systems to integrate information across distinct sources.
  arXiv  Detail & Related papers  (2025-08-28T14:59:55Z)
• Augmented Knowledge Graph Querying leveraging LLMs [2.5311562666866494]
  We introduce SparqLLM, a framework that enhances the querying of Knowledge Graphs (KGs)<n>SparqLLM executes the Extract, Transform, and Load (ETL) pipeline to construct KGs from raw data.<n>It also features a natural language interface powered by Large Language Models (LLMs) to enable automatic SPARQL query generation.
  arXiv  Detail & Related papers  (2025-02-03T12:18:39Z)
• Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models [83.65386456026441]
  Data-Juicer 2.0 is a data processing system backed by 100+ data processing operators spanning text, image, video, and audio modalities.<n>It supports more critical tasks including data analysis, synthesis, annotation, and foundation model post-training.<n>The system is publicly available and has been widely adopted in diverse research fields and real-world products such as Alibaba Cloud PAI.
  arXiv  Detail & Related papers  (2024-12-23T08:29:57Z)
• ToolACE: Winning the Points of LLM Function Calling [139.07157814653638]
  ToolACE is an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data.<n>We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard.
  arXiv  Detail & Related papers  (2024-09-02T03:19:56Z)
• An Integrated Data Processing Framework for Pretraining Foundation Models [57.47845148721817]
  Researchers and practitioners often have to manually curate datasets from difference sources. We propose a data processing framework that integrates a Processing Module and an Analyzing Module. The proposed framework is easy to use and highly flexible.
  arXiv  Detail & Related papers  (2024-02-26T07:22:51Z)
• Trusted Provenance of Automated, Collaborative and Adaptive Data Processing Pipelines [2.186901738997927]
  We provide a solution architecture and a proof of concept implementation of a service, called Provenance Holder. Provenance Holder enables provenance of collaborative, adaptive data processing pipelines in a trusted manner.
  arXiv  Detail & Related papers  (2023-10-17T17:52:27Z)
• Towards Better Dynamic Graph Learning: New Architecture and Unified Library [29.625205125350313]
  DyGFormer is a Transformer-based architecture for dynamic graph learning. DyGLib is a unified library with standard training pipelines and coding interfaces.
  arXiv  Detail & Related papers  (2023-03-23T05:27:32Z)
• A Scalable AutoML Approach Based on Graph Neural Networks [4.723269144709768]
  KGpip is designed as a sub-component for AutoML systems. We demonstrate this ability via integrating KGpip with two AutoML systems and show that it does significantly enhance the performance of existing state-of-the-art systems.
  arXiv  Detail & Related papers  (2021-10-29T20:55:13Z)
• Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation [63.24594955429465]
  Multi-source entity linkage is critical in high-impact applications such as data cleaning and user stitching. AdaMEL is a deep transfer learning framework that learns generic high-level knowledge to perform multi-source entity linkage. Our framework achieves state-of-the-art results with 8.21% improvement on average over methods based on supervised learning.
  arXiv  Detail & Related papers  (2021-10-27T15:20:41Z)
• Better Call the Plumber: Orchestrating Dynamic Information Extraction Pipelines [1.7688094977719888]
  Plumber is the first framework that brings together the research community's disjoint IE efforts. We study the optimization problem of choosing suitable pipelines based on input sentences. Our results demonstrate the effectiveness of Plumber in dynamically generating KG information extraction pipelines.
  arXiv  Detail & Related papers  (2021-02-22T13:14:02Z)
• MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines [29.999324319722508]
  We address two main challenges that arise during the deployment of machine learning pipelines, and address them with the design of versioning for an end-to-end analytics system MLCask. We define and accelerate the metric-driven merge operation by pruning the pipeline search tree using reusable history records and pipeline compatibility information. The effectiveness of MLCask is evaluated through an extensive study over several real-world deployment cases.
  arXiv  Detail & Related papers  (2020-10-17T13:34:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.