Amazon Product Text Evaluation

Product-description evaluation data for assessing language-model outputs against product features.

View source on GitHub ↗Open license stated

What the resource contains

  • Product metadata used in generation prompts
  • Description-related evaluation resources
  • Application-focused quality and factuality tasks

Potential uses

  • Evaluate generated product copy
  • Check factual consistency
  • Study output quality and safety

Access & formats

Text / structured metadata. Repository files. Follow the project’s instructions on GitHub; some resources require external files, registration or approval.

License & reuse

The source explicitly licenses the data under CC BY 4.0. Preserve attribution and review source conditions.

Important limitations

Evaluation examples can include restricted-product topics. Generated descriptions still require factual and domain-specific review before use.

Source & attribution

amazon-science — original GitHub project ↗

Documentation reviewed 2026-09-24. Review scope and licensing notes. Suggest a correction.

Related resources

Shopping AI benchmarks

Shopping MMLU

KL4805

A multitask benchmark for language models across shopping knowledge, reasoning, behavior and languages.

Review required

CSV / JSON · Repository / linked release

Shopping AI benchmarks

WebShop

princeton-nlp

A simulated shopping environment with products and human instructions for training and evaluating web agents.

Review required

JSON / JSONL / environment assets · External dependencies