Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning
This addresses the need for reliable patent intelligence solutions, particularly for small and medium-sized agencies, by enhancing system robustness to colloquial and ambiguous queries, though it is incremental as it builds on existing RAG methods with a focus on fine-tuning.
The paper tackles the problem of inaccurate retrieval and suboptimal responses in Retrieval-Augmented Generation (RAG) systems for Intellectual Property (IP) due to diverse user queries, proposing a lightweight fine-tuning method that improves retrieval accuracy by up to 262.26% and generation quality by up to 53.58% on patent datasets.
Retrieval-Augmented Generation (RAG) systems in the Intellectual Property (IP) field often struggle with diverse user queries, including colloquial expressions, spelling errors, and ambiguous terminology, leading to inaccurate retrieval and suboptimal responses. To address this challenge, we propose Multi-Angle Question Generation and Retrieval Fine-Tuning Method (MQG-RFM), a novel framework that leverages large language models (LLMs) to simulate varied user inquiries and fine-tunes retrieval models to align semantically equivalent but linguistically diverse questions. Unlike complex architectural modifications, MQG-RFM adopts a lightweight Data-to-Tune paradigm, combining prompt-engineered query generation with hard negative mining to enhance retrieval robustness without costly infrastructure changes. Experimental results on a Taiwan patent Q&A dataset show 185.62% improvement in retrieval accuracy on the Patent Consultation dataset and 262.26% improvement on the Novel Patent Technology Report dataset, with 14.22% and 53.58% improvements in generation quality over the baselines, respectively. By bridging the gap between user intent and system comprehension through semantic-aware retrieval optimization, MQG-RFM offers a practical, scalable approach for rapid, cost-effective deployment among small and medium-sized agencies seeking reliable patent intelligence solutions. Additionally, our proposed method has already been adopted by ScholarMate, the largest professional research social networking platform in China, to support real-world development and deployment. A demo version of the instantiated is available at https://github.com/renruntao/patent_rag.