PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding

TL;DR

PatenTEB introduces a comprehensive patent-specific benchmark and a versatile model family trained on multiple tasks, significantly advancing patent text embedding quality and generalization for various patent analysis applications.

Contribution

The paper presents PatenTEB, a new benchmark with 15 tasks and 2.06 million examples, and develops the patembed model family with multi-task training and domain-specific enhancements.

Findings

Patembed-base outperforms previous state-of-the-art on BigPatentClustering.v2.

Patembed-large achieves high NDCG@100 on DAPFAM.

Multi-task training enhances external generalization.

Abstract

Patent text embeddings enable prior art search, technology landscaping, and patent analysis, yet existing benchmarks inadequately capture patent-specific challenges. We introduce PatenTEB, a comprehensive benchmark comprising 15 tasks across retrieval, classification, paraphrase, and clustering, with 2.06 million examples. PatenTEB employs domain-stratified splits, domain specific hard negative mining, and systematic coverage of asymmetric fragment-to-document matching scenarios absent from general embedding benchmarks. We develop the patembed model family through multi-task training, spanning 67M to 344M parameters with context lengths up to 4096 tokens. External validation shows strong generalization: patembed-base achieves state-of-the-art on MTEB BigPatentClustering.v2 (0.494 V-measure vs. 0.445 previous best), while patembed-large achieves 0.377 NDCG@100 on DAPFAM. Systematic ablations reveal that multi-task training improves external generalization despite minor benchmark costs, and that domain-pretrained initialization provides consistent advantages across task families. All resources will be made available at https://github.com/iliass-y/patenteb. Keywords: patent retrieval, sentence embeddings, multi-task learning, asymmetric retrieval, benchmark evaluation, contrastive learning.