The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper presents a hybrid generative-tagging decoding approach for extracting product attribute-value pairs in e-commerce. It combines a tagging head that directly copies frequent attribute values from the source text with a generative head that handles rare attributes and non-copyable values. Experiments integrated with vLLM inference show a 10% increase in attribute coverage, a 63% rise in correct extractions, and a 44% reduction in latency without sacrificing precision.
arXiv:2606. 24655v1 Announce Type: cross Abstract: The explosive growth and complexity of product data within the dynamic Brazilian e-commerce landscape demand robust and specialized methods for structured information extraction.
The paper presents a two‑stage large language model pipeline for e‑commerce attribute extraction. First, it discovers a compact, ranked set of purchase‑discriminative attributes for each product category; second, it extracts those attribute values from catalog text using a fine‑tuned Qwen3‑4B model with Hyper‑Parallel Decoding. The approach attains 85% extraction accuracy while cutting inference costs by 92%, enabling scalable production use and producing consistent, comparable product knowledge bases.
arXiv:2607. 07469v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages.
arXiv:2610.09063v1 Announce Type: new Abstract: Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability c...
The paper introduces NORA, a noise‑robust tagging system for Financial Numerical Entity (FNE) attributes, addressing errors in XBRL‑derived labels and under‑emphasized attributes such as reporting‑time relation, measurement scale, and accounting sign. NORA employs task‑aware instance‑specific weighting to reduce the impact of noisy labels during training and proposes an evaluation protocol that filters noisy labels in real‑world test sets. A large benchmark of 11.4 million FNEs across 6.3 million sentences is constructed, and experiments show NORA outperforms prior models in mean Accuracy and Macro F1, especially for time‑relation prediction.