Llm-powered Real-time Patent Citation Recommendation For Financial Technologies

Abstract

Rapid financial innovation has been accompanied by a sharp increase in patenting activity, making timely and comprehensive prior-art discovery more difficult. This problem is especially evident in financial technologies, where innovations develop quickly, patent collections grow continuously, and citation recommendation systems must be updated as new applications arrive. Existing patent retrieval and citation recommendation methods typically rely on static indexes or periodic retraining, which limits their ability to operate effectively in such dynamic settings. In this study, we propose a real-time patent citation recommendation framework designed for large and fast-changing financial patent corpora. Using a dataset of 428,843 financial patents granted by the China National Intellectual Property Administration (CNIPA) between 2000 and 2024, we build a three-stage recommendation pipeline. The pipeline uses large language model (LLM) embeddings to represent the semantic content of paten

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeng2026llm

Related papers

• Evaluating Llm-based Approaches To Legal Citation Prediction: Domain-specific Pre-training, Fine-tuning, Or RAG? A Benchmark And An Australian Law Case Study (2024)0.00
• Paecter: Patent-level Representation Learning Using Citation-informed Transformers (2024)18.25
• Enhancing Patent Retrieval Using Text And Knowledge Graph Embeddings: A Technical Note (2022)10.07
• Advancing Large Language Models For Spatiotemporal And Semantic Association Mining Of Similar Environmental Events (2024)5.84
• Large Language Model Informed Patent Image Retrieval (2024)0.00
• PLUM: Adapting Pre-trained Language Models For Industrial-scale Generative Recommendations (2025)2.26
• From Interests To Insights: An LLM Approach To Course Recommendations Using Natural Language Queries (2024)0.00
• Bridging Language And Items For Retrieval And Recommendation: Benchmarking Llms As Semantic Encoders (2024)0.00