Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications
#Retrieval-Augmented Generation#Knowledge Graphs#Neural Networks#E-commerce#Information Retrieval#Large Language Models#Structured Data#RAG Systems
📌 Key Takeaways
Researchers published comparative analysis of neural retriever-reranker pipelines for RAG over knowledge graphs
Study addresses challenges in applying RAG to structured data in e-commerce contexts
Results showed 20.4% higher Hit@1 and 14.5% higher Mean Reciprocal Rank over benchmarks
Findings provide framework for integrating domain-specific knowledge bases into generative systems
📖 Full Retelling
Researchers Teri Rumble, Zbyněk Gazdík, Javad Zarrin, and Jagdeep Ahluwalia published a comparative analysis of neural retriever-reranker pipelines for retrieval-augmented generation over knowledge graphs in e-commerce applications on December 14, 2025, addressing challenges in applying RAG to structured data. The research, submitted to arXiv, explores how Retrieval-Augmented Generation (RAG) can be enhanced when applied to structured knowledge graphs rather than just unstructured text, which presents unique challenges in scaling retrieval across connected graphs and preserving contextual relationships during response generation. The study presents and evaluates multiple Retriever-Reranker pipeline configurations optimized for language queries in e-commerce contexts using the STaRK Semi-structured Knowledge Base, a production-scale dataset. Experimental results demonstrate substantial improvements over published benchmarks, achieving 20.4% higher Hit@1 and 14.5% higher Mean Reciprocal Rank, establishing a practical framework for integrating domain-specific knowledge bases into generative systems. The findings provide actionable insights for deploying production-ready RAG systems with implications that extend beyond e-commerce to other domains requiring information retrieval from structured knowledge bases.
🏷️ Themes
Artificial Intelligence, Information Retrieval, E-commerce Technology
Information retrieval (IR) in computing and information science is the task of identifying and retrieving information system resources that are relevant to an information need. The information need can be specified in the form of a search query. In the case of document retrieval, queries can be base...
A neural network is a group of interconnected units called neurons that send signals to one another. Neurons can be either biological cells or mathematical models. While individual neurons are simple, many of them together in a network can perform complex tasks.
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pre-trained transformers (GPTs) that provide the c...
--> Computer Science > Information Retrieval arXiv:2602.22219 [Submitted on 14 Dec 2025] Title: Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications Authors: Teri Rumble , Zbyněk Gazdík , Javad Zarrin , Jagdeep Ahluwalia View a PDF of the paper titled Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications, by Teri Rumble and 3 other authors View PDF HTML Abstract: Recent advancements in Large Language Models have transformed Natural Language Processing , enabling complex information retrieval and generation tasks. Retrieval-Augmented Generation has emerged as a key innovation, enhancing factual accuracy and contextual grounding by integrating external knowledge sources with generative models. Although RAG demonstrates strong performance on unstructured text, its application to structured knowledge graphs presents challenges: scaling retrieval across connected graphs and preserving contextual relationships during response generation. Cross-encoders refine retrieval precision, yet their integration with structured data remains underexplored. Addressing these challenges is crucial for developing domain-specific assistants that operate in production environments. This study presents the design and comparative evaluation of multiple Retriever-Reranker pipelines for knowledge graph natural language queries in e-Commerce contexts. Using the STaRK Semi-structured Knowledge Base , a production-scale e-Commerce dataset, we evaluate multiple RAG pipeline configurations optimized for language queries. Experimental results demonstrate substantial improvements over published benchmarks, achieving 20.4% higher Hit@1 and 14.5% higher Mean Reciprocal Rank . These findings establish a practical framework for integrating domain-specific SKBs into generative systems. Our contributions provide actionable insig...
