# Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching

arXiv: https://arxiv.org/abs/2608.11030 · HTML: https://mlsanity.com/paper/2608.11030/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 18 of 18)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards](https://mlsanity.com/paper/2410.13509/) (2024)
- [Can Large Language Models Generate High-quality Patent Claims?](https://mlsanity.com/paper/2406.19465/) (2024)
- [PatentMatch: A Dataset for Matching Patent Claims & Prior Art](https://mlsanity.com/paper/2012.13919/) (2020)
- [A Text-Embedding-based Approach to Measure Patent-to-Patent Technological Similarity -- Workflow, Code, and Applications](https://mlsanity.com/paper/2003.12303/) (2020)
- [PatentGPT: A Large Language Model for Intellectual Property](https://mlsanity.com/paper/2404.18255/) (2024)
- [MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property](https://mlsanity.com/paper/2402.16389/) (2024)
- [Large Language Model for Patent Concept Generation](https://mlsanity.com/paper/2409.00092/) (2024)
- [Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph](https://mlsanity.com/paper/2504.14845/) (2025)
- [A comparative analysis of embedding models for patent similarity](https://mlsanity.com/paper/2403.16630/) (2024)
- [Towards Automated Patent Workflows: AI-Orchestrated Multi-Agent Framework for Intellectual Property Management and Analysis](https://mlsanity.com/paper/2409.19006/) (2024)

## Abstract (arXiv)

Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex structure of patent documents, dense technical terminology, and multi-modal information, traditional methods struggle to accurately identify subtle differences between patents. Existing LLM-based patent matching approaches typically rely on domain-specific pretrained or instruction tuning, which often entail high manual labeling costs and catastrophic forgetting. While retrieval-augmented generation (RAG) methods introduce external knowledge they fail to fully leverage LLM's capability to automatically parse patents and mine deep semantic relationships. To address these limitations, this paper proposes a self-knowledge RAG framework that guides LLMs to autonomously extract key technical entities and construct hierarchical ontological structures from patent matching queries, thereby enabling query expansion and precise retrieval. The method integrates the FAISS retrieval with a generative matching mechanism, leveraging self-knowledge to enhance the model's understanding of patent innovations and significantly improve retrieval and matching accuracy. Experimental results demonstrate the outstanding performance of the proposed method on real-world patent datasets, validating its effectiveness and application potential.