cs.IR · 2607.00003 Copy arXiv ID · Apr 18, 2026 Save From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems Authors: Abhirup Dasgupta , Fernando Spadea , Oshani Seneviratne
Organizations: Rensselaer Polytechnic Institute, Troy NY 12180, USA
Abstract Personal Knowledge Graphs (PKGs) offer a privacy-preserving framework for modeling user preferences, yet constructing them from unstructured, decentralized conversational data remains a challenge. This paper bridges the gap between conversational "strings" and semantic "things" by presenting a reproducible pipeline for extracting structured user-preference triples using lightweight Large Language Models. We evaluate Qwen- and Gemma-based models on their ability to extract RDF-compliant triples linked to Wikidata identifiers from conversational data for PKG construction. Our evaluation assesses both the semantic extraction fidelity and the utility of the resulting graphs in a downstream recommendation task. We found that certain models performed well and had proportionally high downstream performance relative to their triple extraction performance.
Explore similar work Sep 12, 2026 · Harshdeep Singh, Yurui Zhu, Giovanni Colavizza +1 Knowledge Graphs Sparql
Apr 21, 2026 · Qiubai Zhu, Qingwang Wang, Haibin Yuan +2 Knowledge Graphs Graph Language Models
Jul 13, 2026 · Mikhail Komarov, Ivan Bondarenko, Stanislav Shtuka +5 Graph-Based Retrieval Augmented Generation Knowledge Graphs
Sep 12, 2026 · cs.AI J/K move · Enter open · S save
Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small graph samples, rather than task-specific fine-tuning? We integrate VoID descriptions and ShEx schemas into a retrieval-augmented generation (RAG) pipeline and ablate KG-derived context on the SciQA benchmark. Our best configuration -- combining ShEx schemas, retrieved triples, and example question-query pairs -- reaches an exact match of 0.419 on execution results without any LLM fine-tuning. We further find that lexical metrics such as F1 poorly predict query correctness, and that larger general-purpose LLMs can outperform smaller code-specialized ones once given sufficient context. Second, we ask how to generate the structured metadata that this method relies on from very large KGs, where KG metadata generation becomes computationally intractable. We introduce a predicate-coverage-aware parallel graph sampling strategy that preserves structural diversity while remaining computationally tractable. On OpenCitations Meta and GESIS, it retains high predicate coverage with minimal triple loss and reduces runtime by over 80x; on ORKG, sampling is not just faster but the only tractable path to obtain complete metadata. Together, these results show that structured schema context and lightweight prompting can substantially reduce reliance on fine-tuning for scalable conversational access to KGs, though closing the remaining gap to fully fine-tuned approaches will likely require reducing dependence on curated question-query exemplars -- whether through synthetic generation or an execution-feedback-driven approach -- and validating these findings beyond a single benchmark.