Contextually Aware E-Commerce Product Question Answering using RAG

• URL: http://arxiv.org/abs/2508.01990v1
• Date: Mon, 04 Aug 2025 02:14:07 GMT
• Title: Contextually Aware E-Commerce Product Question Answering using RAG
• Authors: Praveen Tangarajan, Anand A. Rajasekar, Manish Rathi, Vinay Rao Dandin, Ozan Ersoy,
• Abstract summary: E-commerce product pages contain a mix of structured specifications, unstructured reviews, and contextual elements like personalized offers or regional variants.<n>We propose a scalable, end-to-end framework for e-commerce Product Question Answering (PQA) using Retrieval Augmented Generation (RAG)<n>Our system leverages conversational history, user profiles, and product attributes to deliver relevant and personalized answers.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• PDF Retrieval Augmented Question Answering [14.617711623828248]
  This paper presents an advancement in Question-Answering (QA) systems using a Retrieval Augmented Generation (RAG) framework.<n>We seek to develop a comprehensive RAG-based QA system that will effectively address complex multimodal questions.
  arXiv  Detail & Related papers  (2025-06-22T13:14:19Z)
• Unanswerability Evaluation for Retrieval Augmented Generation [74.3022365715597]
  UAEval4RAG is a framework designed to evaluate whether RAG systems can handle unanswerable queries effectively.<n>We define a taxonomy with six unanswerable categories, and UAEval4RAG automatically synthesizes diverse and challenging queries.
  arXiv  Detail & Related papers  (2024-12-16T19:11:55Z)
• STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases [93.96463520716759]
  We develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in precision medicine. We design a novel pipeline to synthesize realistic user queries that integrate diverse relational information and complex textual properties.
  arXiv  Detail & Related papers  (2024-04-19T22:54:54Z)
• A Usage-centric Take on Intent Understanding in E-Commerce [20.648271216249977]
  We focus on predicative user intents as "how a customer uses a product" We identify two weaknesses of FolkScope, the SOTA E-Commerce Intent Graph. They limit its ability to strongly align user intents with products having the most desirable property.
  arXiv  Detail & Related papers  (2024-02-22T18:09:33Z)
• CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models [49.16989035566899]
  Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios.
  arXiv  Detail & Related papers  (2024-01-30T14:25:32Z)
• A case study of Generative AI in MSX Sales Copilot: Improving seller productivity with a real-time question-answering system for content recommendation [3.680292844010173]
  We design a real-time question-answering system specifically targeted for helping sellers get relevant material/documentation they can share live with their customers or refer to during a call. We take the Seismic content repository as a relatively large scale example of a diverse dataset of sales material. We achieve this by engineering prompts in an elaborate fashion that makes use of the rich set of meta-features available for documents and sellers.
  arXiv  Detail & Related papers  (2024-01-04T13:32:44Z)
• Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations [66.16863141262506]
  We present a novel approach that focuses on generating internet search queries guided by social commonsense. Our proposed framework addresses passive user interactions by integrating topic tracking, commonsense response generation and instruction-driven query generation.
  arXiv  Detail & Related papers  (2023-10-22T16:14:56Z)
• Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling [62.049330405736406]
  Product Question Answering (PQA) on E-Commerce platforms has attracted increasing attention as it can act as an intelligent online shopping assistant. It is insufficient to provide the same "completely summarized" answer to all customers, since many customers are more willing to see personalized answers with customized information only for themselves. We propose a novel multi-perspective user preference model for generating personalized answers in PQA.
  arXiv  Detail & Related papers  (2021-12-27T07:51:49Z)
• Distantly Supervised Transformers For E-Commerce Product QA [5.460297795256275]
  We propose a practical instant question answering (QA) system on product pages of ecommerce services. For each user query, relevant community question answer (CQA) pairs are retrieved. Our proposed transformer-based model learns a robust relevance function by jointly learning unified syntactic and semantic representations.
  arXiv  Detail & Related papers  (2021-04-07T06:37:16Z)
• User-Inspired Posterior Network for Recommendation Reason Generation [53.035224183349385]
  Recommendation reason generation plays a vital role in attracting customers' attention as well as improving user experience. We propose a user-inspired multi-source posterior transformer (MSPT), which induces the model reflecting the users' interests. Experimental results show that our model is superior to traditional generative models.
  arXiv  Detail & Related papers  (2021-02-16T02:08:52Z)

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.