Product Attribute Extraction

Follow this topic Ask about this topic

Latest papers

15 papers1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value Extraction
Oct 15, 2026Keshav Kolluru, Manas Gupta, Maroof Ahmad +1Product Attribute Extraction Document Information Extraction
Amazon
Scaling E-Commerce Attribute Extraction with Parallel Decoding
Sep 9, 2026Nikhita Vedula, Dushyanta Dhyani, Bryan Wang +1Document Information Extraction Product Attribute Extraction
Amazon.com, Inc.
The MODA General Attribute Suite: A Four-Track Evaluation Benchmark for Fashion Attribute Extraction
Sep 8, 2026Arkid MitraProduct Attribute Extraction
Hopit AI
Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos
Sep 6, 2026Tong Wu, Ming Cheng, Jiazhen Hu +2Product Attribute Extraction VLM Reasoning
Virginia Tech · Amazon
CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search
Aug 25, 2026Xiaolong Sun, Qichao Wang, Hangyu Li +1E-Commerce Search Product Attribute Extraction
Sun Yat-Sen University, Guangzhou, China · Nanyang Technological University, Singapore · Tencent, Shenzhen, China
TRACE: Agentic Catalog Enrichment with Multi-source Evidence Grounding
Aug 21, 2026Rohan Kumar, Steven Xu, Kyle MacDonald +4Product Attribute Extraction LLM Information Extraction
DoorDash, Inc.
Enhancing Generative Information Extraction with Two-step Validation: A Product Attribute Use Case
Jul 29, 2026Yi-Sheng Hsu, Nermeen Abou Baker, Uwe HandmannDocument Information Extraction Product Attribute Extraction
Computer Science Institute, Ruhr West University of Applied Sciences Bottrop, Germany
CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models
Jul 15, 2026Zhu Cheng, Zhenming Wang, Yu +14Document Information Extraction Product Attribute Extraction
Xuan · Amazon, Seattle, USA
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
Jul 8, 2026Andrea Scarinci, Virginia Negri, Brayan Impata +3LLM-as-a-Judge LLM-Assisted Annotation
Amazon
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
Jun 26, 2026Oxygen AIIC, Chan Long, Chao Liu +52Product Attribute Extraction Knowledge Representation
AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach
Jun 23, 2026Murilo Gazzola, Hugo Gobato Souto, Samuel Silva +4Document Information Extraction Product Attribute Extraction
LuizaLabs – Center of Excellence in Artificial Intelligence S˜ao Paulo, SP – Brazil · Department of Computing and Informatics – Mackenzie Presbyterian University S˜ao Paulo, SP – Brazil · Institute of Mathematics and Computer Sciences - University of S˜ao Paulo S˜ao Carlos, SP – Brazil
IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products
Jun 12, 2026Haonan Qi, Jin Cao, Yongqi Zhang +9Multimodal Large Language Models Multimodal Model Evaluation
Multimodal and Industrial AI TeamTaobao&Tmall, Alibaba Group
Fashion Florence: Fine-Tuning Florence-2 for Structured Fashion Attribute Extraction
May 11, 2026Anushree BerliaVLM Adaptation Multimodal Foundation Models
AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction
Apr 18, 2026Pollawat Hongwimol, Haoning Shang, Chutong Wang +6KG Construction Document Information Extraction
Lazada, Alibaba International Digital Commerce Group · Nanyang Technological University, Singapore
Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements
Dec 7, 2024Filippos Ventirozos, Ioanna Nteka, Tania Nandy +4Document Information Extraction Product Attribute Extraction
Manchester Metropolitan University, John Dalton tower, Chester St, Manchester M1 5GD, UK · Auto Trader UK, 1 Tony Wilson Place, Manchester M15 4FN, UK

Oct 15, 2026J/K move · Enter open · S save

Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value Extraction

Keshav Kolluru, Manas Gupta, Maroof Ahmad, Suchitra Sathyanarayana

Amazon

Product Attribute Extraction Document Information Extraction LLM Information Extraction

Open paper AskPDF arXiv

Attribute-value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging strategies for extracting the attribute names and their corresponding values. Tagging models directly label spans in the source, making them fast and grounded, but they cannot produce values that require reformatting or generate rare attribute names outside their label space. Generative models avoid these drawbacks by generating both attribute names and values token by token, but this auto-regressive nature makes them slow and limits attribute coverage. We introduce hybrid generative-tagging decoding, a novel model architecture that combines tagging source spans and open-ended generation. For frequent attributes whose values are copyable, a tagging head extracts values directly from the source. This lets the generative head focus on the remainder - rare attributes outside the tagger's label space and non-copyable values, including implicit or normalized values. Integrated into vLLM inference, the hybrid decoder raises attribute coverage by 10% and extracts 63% more correct attribute-value pairs at no precision cost, while reducing latency by 44%.