Contextually Aware E-Commerce Product Question Answering using RAG

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tangarajan, Praveen, Rajasekar, Anand A., Rathi, Manish, Dandin, Vinay Rao, Ersoy, Ozan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911090034606080
author Tangarajan, Praveen
Rajasekar, Anand A.
Rathi, Manish
Dandin, Vinay Rao
Ersoy, Ozan
author_facet Tangarajan, Praveen
Rajasekar, Anand A.
Rathi, Manish
Dandin, Vinay Rao
Ersoy, Ozan
contents E-commerce product pages contain a mix of structured specifications, unstructured reviews, and contextual elements like personalized offers or regional variants. Although informative, this volume can lead to cognitive overload, making it difficult for users to quickly and accurately find the information they need. Existing Product Question Answering (PQA) systems often fail to utilize rich user context and diverse product information effectively. We propose a scalable, end-to-end framework for e-commerce PQA using Retrieval Augmented Generation (RAG) that deeply integrates contextual understanding. Our system leverages conversational history, user profiles, and product attributes to deliver relevant and personalized answers. It adeptly handles objective, subjective, and multi-intent queries across heterogeneous sources, while also identifying information gaps in the catalog to support ongoing content improvement. We also introduce novel metrics to measure the framework's performance which are broadly applicable for RAG system evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01990
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contextually Aware E-Commerce Product Question Answering using RAG
Tangarajan, Praveen
Rajasekar, Anand A.
Rathi, Manish
Dandin, Vinay Rao
Ersoy, Ozan
Computation and Language
I.2.7; H.3.3
E-commerce product pages contain a mix of structured specifications, unstructured reviews, and contextual elements like personalized offers or regional variants. Although informative, this volume can lead to cognitive overload, making it difficult for users to quickly and accurately find the information they need. Existing Product Question Answering (PQA) systems often fail to utilize rich user context and diverse product information effectively. We propose a scalable, end-to-end framework for e-commerce PQA using Retrieval Augmented Generation (RAG) that deeply integrates contextual understanding. Our system leverages conversational history, user profiles, and product attributes to deliver relevant and personalized answers. It adeptly handles objective, subjective, and multi-intent queries across heterogeneous sources, while also identifying information gaps in the catalog to support ongoing content improvement. We also introduce novel metrics to measure the framework's performance which are broadly applicable for RAG system evaluations.
title Contextually Aware E-Commerce Product Question Answering using RAG
topic Computation and Language
I.2.7; H.3.3
url https://arxiv.org/abs/2508.01990