From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Yilun, Vedula, Nikhita, Malmasi, Shervin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918475400740864
author Zhu, Yilun
Vedula, Nikhita
Malmasi, Shervin
author_facet Zhu, Yilun
Vedula, Nikhita
Malmasi, Shervin
contents Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle to capture nuanced context-specific attribute relevance. In this paper, we present a two-stage approach combining Large Language Model (LLM)-driven attribute graph construction with graph-aware LLM ranking. In the offline stage, we extract structured product attributes from unstructured text, and construct a reusable attribute graph with category-aware schemas. In the online stage, we rank retrieved candidates by reasoning over this structured representation rather than raw text, reducing per-product token usage by 57% while improving ranking precision. Experiments show that our approach outperforms multiple baselines under zero-shot scenarios, achieving a over 5% improvement in average precision without requiring training data, generalizes robustly across diverse product categories, and shows immense potential for real-world deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27410
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking
Zhu, Yilun
Vedula, Nikhita
Malmasi, Shervin
Information Retrieval
Computation and Language
Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle to capture nuanced context-specific attribute relevance. In this paper, we present a two-stage approach combining Large Language Model (LLM)-driven attribute graph construction with graph-aware LLM ranking. In the offline stage, we extract structured product attributes from unstructured text, and construct a reusable attribute graph with category-aware schemas. In the online stage, we rank retrieved candidates by reasoning over this structured representation rather than raw text, reducing per-product token usage by 57% while improving ranking precision. Experiments show that our approach outperforms multiple baselines under zero-shot scenarios, achieving a over 5% improvement in average precision without requiring training data, generalizes robustly across diverse product categories, and shows immense potential for real-world deployment.
title From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2604.27410