DeepPlanning: Long-Horizon Shopping Item Retrieval for E-Commerce

DeepPlanning is a procedural retrieval task from the Massive Text Embedding Benchmark (MTEB). It is based on the Long-horizon Memory Embedding Benchmark (LMEB) and focuses on retrieving shopping items needed to support long-horizon planning queries. The dataset was uploaded by 'mteb' and last updated on 2026-05-11.

Use Cases

• Benchmarking text embedding models on long-horizon planning tasks based on the described retrieval scenario.
• Evaluating model performance on procedural retrieval for e-commerce shopping based on the stated domain.
• Researching text-to-text retrieval for complex, multi-step queries as indicated by the task category.

Strengths

• Part of the established Massive Text Embedding Benchmark (MTEB), suggesting a standardized evaluation framework.
• Specifically designed for the long-horizon planning domain, as indicated by its reference to the LMEB.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and sample data are unknown, which may limit suitability assessment.

Provenance

Source

KaLM-Embedding/LMEB via the MTEB framework on Hugging Face.

Collection Method

Likely constructed as a benchmark task for evaluating text embedding models.

Freshness

Last updated 2026-05-11 15:54:30; freshness should be verified.