# AmazonQA: A Review-Based Question Answering Task

arXiv: https://arxiv.org/abs/1908.04364 · HTML: https://mlsanity.com/paper/1908.04364/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2019.

## Built on by (most cited first, 30 of 43)

- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data](https://mlsanity.com/paper/2402.08831/) (2024)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://mlsanity.com/paper/2209.06638/) (2022)
- [English Machine Reading Comprehension Datasets: A Survey](https://mlsanity.com/paper/2101.10421/) (2021)
- [Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models](https://mlsanity.com/paper/2410.20745/) (2024)
- [Contextual Document Embeddings](https://mlsanity.com/paper/2410.02525/) (2024)
- [Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling](https://mlsanity.com/paper/2112.13556/) (2021)
- [NeoBERT: A Next-Generation BERT](https://mlsanity.com/paper/2502.19587/) (2025)
- [F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World](https://mlsanity.com/paper/2603.19223/) (2026)
- [Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning](https://mlsanity.com/paper/2204.02725/) (2022)
- [Product Question Answering in E-Commerce: A Survey](https://mlsanity.com/paper/2302.08092/) (2023)
- [WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.08643/) (2025)
- [F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data](https://mlsanity.com/paper/2510.02294/) (2025)
- [Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data](https://mlsanity.com/paper/2410.17337/) (2024)
- [QUADRo: Dataset and Models for QUestion-Answer Database Retrieval](https://mlsanity.com/paper/2304.01003/) (2023)
- [Database-Augmented Query Representation for Information Retrieval](https://mlsanity.com/paper/2406.16013/) (2024)
- [EcomMMMU: Strategic Utilization of Visuals for Robust Multimodal E-commerce Models](https://mlsanity.com/paper/2508.15721/) (2025)
- [AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt](https://mlsanity.com/paper/2509.15159/) (2025)
- [BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain](https://mlsanity.com/paper/2409.20075/) (2024)
- [LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations](https://mlsanity.com/paper/2509.12539/) (2025)
- [Distantly Supervised Transformers For E-Commerce Product QA](https://mlsanity.com/paper/2104.02947/) (2021)
- [PLAtE: A Large-scale Dataset for List Page Web Extraction](https://mlsanity.com/paper/2205.12386/) (2022)
- [UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt](https://mlsanity.com/paper/2309.11065/) (2023)
- [Generative Representational Learning of Foundation Models for Recommendation](https://mlsanity.com/paper/2506.11999/) (2025)

## Abstract (arXiv)

Every day, thousands of customers post questions on Amazon product pages. After some time, if they are fortunate, a knowledgeable customer might answer their question. Observing that many questions can be answered based upon the available product reviews, we propose the task of review-based QA. Given a corpus of reviews and a question, the QA system synthesizes an answer. To this end, we introduce a new dataset and propose a method that combines information retrieval techniques for selecting relevant reviews (given a question) and "reading comprehension" models for synthesizing an answer (given a question and review). Our dataset consists of 923k questions, 3.6M answers and 14M reviews across 156k products. Building on the well-known Amazon dataset, we collect additional annotations, marking each question as either answerable or unanswerable based on the available reviews. A deployed system could first classify a question as answerable and then attempt to generate an answer. Notably, unlike many popular QA datasets, here, the questions, passages, and answers are all extracted from real human interactions. We evaluate numerous models for answer generation and propose strong baselines, demonstrating the challenging nature of this new task.