构建专利文本嵌入的综合性评测基准与模型家族，提升专利检索与分析能力。
PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding
- 设计15项任务覆盖专利检索、分类等场景，含206万样本和领域分层划分
- patembed系列模型在大模型参数量达3.44亿，支持4096词长上下文
- 多任务训练提升泛化性，适合需要高精度专利分析的研究与工业应用
专利文本嵌入可支持现有技术检索、技术布局分析与专利评估，但现有评测基准未能充分反映专利特有的挑战。我们提出PatenTEB，一个包含15项任务的综合性基准，涵盖检索、分类、重述与聚类，共206万条数据。该基准采用领域分层划分、领域特定难负样本挖掘，并系统覆盖通用嵌入基准缺失的非对称片段-文档匹配场景。通过多任务训练，我们构建了patembed模型家族，参数量从6700万至3.44亿，支持最长4096个词的上下文。外部验证显示：patembed-base在MTEB BigPatentClustering.v2上取得0.494的V-measure（前最佳0.445），patembed-large在DAPFAM上达到0.377 NDCG@100。系统消融实验表明，多任务训练虽小幅增加基准开销，但显著提升外部泛化能力；领域预训练初始化在各类任务中均带来稳定优势。所有资源将开源至https://github.com/iliass-y/patenteb。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。