Rethinking patent retrieval with language models: Toward scalable and efficient search

Rethinking patent retrieval with language models: Toward scalable and efficient search

Journal article

1 volume.

Semantic search with embedding models offers an alternative to traditional keyword-based patent retrieval but often struggles with computational cost and efficiency in real-time scenarios compared to methods like BM25. Meanwhile, the rapid advancement of language models raises questions about the necessity of domain-specific models versus the viability of general-purpose ones. This work presents a comprehensive evaluation of embedding-based patent search using the CLEF-IP 2011 dataset. We assess 10 configurations employing language models as retrievers, re-rankers, or hybrids, across 9 models, both patent-specific and general-purpose, tested in 105 experimental setups. Our best configurations deliver a 14.81% absolute MAP improvement over state-of-the-art baselines and outperform patent-specific embeddings by at least 28.95% in MAP. We further show that embedding quantization enables large-scale patent search with up to 30×faster retrieval and 32×lower memory usage. These results provide practical guidance for integrating embedding models into patent prior art search while addressing performance and scalability constraints.

Crossref

World Patent Information ; 84, March, 2026

World Patent Information

Oxford [England] : Elsevier Ltd., 2026.

English

https://www.sciencedirect.com/science/article/abs/pii/S0172219023000108

External Online Journals > World Patent Information