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

• URL: http://arxiv.org/abs/2607.00003v1
• Date: Sat, 18 Apr 2026 12:23:42 GMT
• Title: From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems
• Abstract summary: This paper bridges the gap between conversational "strings" and semantic "things" by presenting a reproducible pipeline for extracting structured user-preference triples.<n>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.
• Score: 42.94040983864023
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• GARDRec: Decision-Level Graph Grounding for Large Language Model Recommendation [19.913416708367503]
  We propose emphGARDRec, a Graph-grounded Adaptive Reasoning and Decision-aware Recommendation framework for next-item ranking.<n>GARDRec constructs semantic-structural item representations from textual node features and graph propagation.<n>Experiments show that GARDRec generally improves candidate-ranking performance over representative baselines.
  arXiv  Detail & Related papers  (2026-08-01T13:44:04Z)
• KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quality from Text [6.373904244962351]
  We propose a novel, interpretable metric for intrinsic Knowledge Graph quality assessment.<n>It measures how closely an automatically extracted graph approximates an "ideal" graph.<n>We evaluate our metric across multiple state-of-the-art triple extraction systems and datasets.
  arXiv  Detail & Related papers  (2026-07-11T08:45:15Z)
• Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs [48.16012222834734]
  We introduce a relation set completion task (RSC) and a relation set Embedding model (RelSetE)<n>RSC aims to reason about missing relations that are semantically compatible with a given entity.<n>RelSetE models latent patterns among the observed relations of entities to infer missing ones.
  arXiv  Detail & Related papers  (2026-06-29T06:54:40Z)
• OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion [5.1405091437027455]
  We present OMNIA, a two-stage approach that bridges structural and semantic reasoning for Knowledge Graph Completion.<n>It first generates candidate triples by clustering semantically related entities and relations within the KG, then validates them through lightweight embedding filtering.<n>It significantly improves F1-score compared to traditional embedding-based models.
  arXiv  Detail & Related papers  (2026-03-12T11:30:41Z)
• Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval [22.33550491040999]
  RAG grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents.<n>We build two plug-and-play retrievers: StatementGraphRAG and TopicGraphRAG.<n>Our methods outperform naive chunk-based RAG achieving an average relative improvement of 23.1% in retrieval recall and correctness.
  arXiv  Detail & Related papers  (2025-06-09T17:58:35Z)
• Knowledge Graph Completion with Relation-Aware Anchor Enhancement [50.50944396454757]
  We propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC)<n>We first generate anchor entities within the relation-aware neighborhood of the head entity.<n>Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching.
  arXiv  Detail & Related papers  (2025-04-08T15:22:08Z)
• TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation [50.23504065567638]
  This paper introduces textbfTD3, a novel textbfDataset textbfDistillation method within a meta-learning framework.<n> TD3 distills a fully expressive emphsynthetic sequence summary from original data.<n>An augmentation technique allows the learner to closely fit the synthetic summary, ensuring an accurate update of it in the emphouter-loop.
  arXiv  Detail & Related papers  (2025-02-05T03:13:25Z)
• Learning to Extract Structured Entities Using Language Models [52.281701191329]
  Recent advances in machine learning have significantly impacted the field of information extraction. We reformulate the task to be entity-centric, enabling the use of diverse metrics. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP metric.
  arXiv  Detail & Related papers  (2024-02-06T22:15:09Z)
• Contextualization Distillation from Large Language Model for Knowledge Graph Completion [51.126166442122546]
  We introduce the Contextualization Distillation strategy, a plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models to transform compact, structural triplets into context-rich segments. Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach.
  arXiv  Detail & Related papers  (2024-01-28T08:56:49Z)
• Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction [43.50683283748675]
  Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of fully labeled data. Recent advanced Large Language Models (LLMs), such as ChatGPT and LLaMA, exhibit impressive long-text generation capabilities.
  arXiv  Detail & Related papers  (2024-01-24T17:04:28Z)
• AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators [98.11286353828525]
  GPT-3.5 series models have demonstrated remarkable few-shot and zero-shot ability across various NLP tasks. We propose AnnoLLM, which adopts a two-step approach, explain-then-annotate. We build the first conversation-based information retrieval dataset employing AnnoLLM.
  arXiv  Detail & Related papers  (2023-03-29T17:03:21Z)
• Modeling Multi-Granularity Hierarchical Features for Relation Extraction [26.852869800344813]
  We propose a novel method to extract multi-granularity features based solely on the original input sentences. We show that effective structured features can be attained even without external knowledge.
  arXiv  Detail & Related papers  (2022-04-09T09:44:05Z)

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.