From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems

Abhirup Dasgupta; Fernando Spadea; Oshani Seneviratne

From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems

信息检索 2026-04-18 v1 人工智能

作者: Abhirup Dasgupta , Fernando Spadea , Oshani Seneviratne

摘要

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.

引用

@article{arxiv.2607.00003,
  title  = {From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems},
  author = {Abhirup Dasgupta and Fernando Spadea and Oshani Seneviratne},
  journal= {arXiv preprint arXiv:2607.00003},
  year   = {2026}
}