Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search

• URL: http://arxiv.org/abs/2607.05970v1
• Date: Tue, 07 Jul 2026 08:04:47 GMT
• Title: Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search
• Abstract summary: We study six metadata-generation settings for RDF datasets, ranging from simple rewriting to profile-grounded and agentic graph-based generation.<n>Unconstrained metadata rewriting delivers the strongest retrieval gains over the original metadata, but it is also the least faithful.<n>More grounded settings substantially improve faithfulness, and profile-grounded rewriting provides the most balanced trade-off between retrieval effectiveness and grounding.
• Score: 0.7734726150561086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dataset search depends heavily on metadata, making LLM-generated metadata a consequential form of synthetic content in retrieval systems. We study six metadata-generation settings for RDF datasets, ranging from simple rewriting to profile-grounded and agentic graph-based generation, and evaluate them jointly for retrieval effectiveness and faithfulness. Unconstrained metadata rewriting delivers the strongest retrieval gains over the original metadata, but it is also the least faithful, showing that search improvements can be driven by unsupported semantic expansion. More grounded settings substantially improve faithfulness, and profile-grounded rewriting provides the most balanced trade-off between retrieval effectiveness and grounding. These findings position synthetic metadata as a system-level IR problem in which effectiveness, provenance, and trust must be evaluated together.

Related papers

• Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents [68.52563127206808]
  Structure-aware Retrieval Augmented Generation (SA-RAG) uses tables as an intermediate structured representation to provide a compact and controllable interface.<n>We introduce a quality-aware table metadata generation framework that models metadata normalization and effectiveness.<n>Experiments on two noisy real-world datasets show that SA-RAG significantly outperforms existing RAG baselines.
  arXiv  Detail & Related papers  (2026-05-23T03:07:33Z)
• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs [66.63911043019294]
  Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them.<n>This paper focuses on the use of LLM techniques to prepare data for diverse downstream tasks.<n>We introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning, standardization, error processing, imputation, data integration, and data enrichment.
  arXiv  Detail & Related papers  (2026-01-22T12:02:45Z)
• A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems [0.0]
  This research presents a systematic framework for metadata enrichment using large language models (LLMs) to enhance document retrieval in Retrieval-Augmented Generation (RAG) systems.<n>Our approach employs a comprehensive, structured pipeline that dynamically generates meaningful metadata for document segments.
  arXiv  Detail & Related papers  (2025-12-05T04:05:06Z)
• Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining [45.51273144181658]
  We investigate a wider range of metadata types and find other types of metadata, such as fine-grained indicators of document quality.<n>We introduce metadata appending as a means of improving training efficiency.<n>We analyze latent representations to understand how metadata shapes learning.
  arXiv  Detail & Related papers  (2025-11-26T17:36:31Z)
• Repurposing Synthetic Data for Fine-grained Search Agent Supervision [81.95597592711688]
  LLM-based search agents are increasingly trained on entity-centric synthetic data.<n> prevailing training methods discard this rich entity information, relying instead on sparse, outcome-based rewards.<n>We introduce Entity-aware Group Relative Policy Optimization (E-GRPO), a novel framework that formulates a dense entity-aware reward function.
  arXiv  Detail & Related papers  (2025-10-28T17:50:40Z)
• Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering [0.0]
  We introduce a sophisticated indexing pipeline to create contextually rich document chunks.<n>We benchmark a spectrum of enhancements, including pre-retrieval filtering, post-retrieval reranking, and enriched embeddings.<n>Our proposed optimal architecture combines LLM-driven pre-retrieval optimizations with these contextual embeddings to achieve superior performance.
  arXiv  Detail & Related papers  (2025-10-28T13:16:36Z)
• MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs [48.73595915402094]
  MOLE is a framework that automatically extracts metadata attributes from scientific papers covering datasets of languages other than Arabic.<n>Our methodology processes entire documents across multiple input formats and incorporates robust validation mechanisms for consistent output.
  arXiv  Detail & Related papers  (2025-05-26T10:31:26Z)
• Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval [49.669503570350166]
  Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task.<n>Existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively.<n>We propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking.
  arXiv  Detail & Related papers  (2025-04-07T15:27:37Z)
• Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs [1.1957520154275776]
  Data catalogs serve as repositories for organizing and accessing diverse collection of data assets.<n>Many data catalogs within organizations suffer from limited searchability due to inadequate metadata like asset descriptions.<n>This paper explores the challenges associated with metadata creation and proposes a unique prompt enrichment idea of leveraging existing metadata content.
  arXiv  Detail & Related papers  (2025-03-12T02:33:33Z)
• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• Understanding Synthetic Context Extension via Retrieval Heads [51.8869530817334]
  We investigate fine-tuning on synthetic data for three long-context tasks that require retrieval and reasoning.<n>We find that models trained on synthetic data fall short of the real data, but surprisingly, the mismatch can be interpreted.<n>Our results shed light on how to interpret synthetic data fine-tuning performance and how to approach creating better data for learning real-world capabilities over long contexts.
  arXiv  Detail & Related papers  (2024-10-29T17:55:00Z)
• Corrective Retrieval Augmented Generation [36.04062963574603]
  Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
  arXiv  Detail & Related papers  (2024-01-29T04:36:39Z)

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.