Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 2 of its 17 references that are in the map. First posted on arXiv 7 Jul 2026.
Builds on
2 of 17 references.
References · 2
- 2020Dataset Discovery in Data Lakescited by 31
- 2025AutoDDG: Automated Dataset Description Generation using Large Language Modelscited by 8
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Leveraging Retrieval Augmented Generative LLMs For Automated Metadata Description Generation to Enhance Data Catalogs
- 2026Utilizing Metadata for Better Retrieval-Augmented Generation
- 2026Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
- 2024Metadata-based Data Exploration with Retrieval-Augmented Generation for Large Language Models
- 2026Do Data Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval
- 2026RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora
- 2025A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems
- 2026Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment