Metraipolis › archive › dc_eb28ec98f8b6
Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching — arXiv:2608.11030
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11030
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:14:32.593Z
- SHA-256 of the archived text
6e07c19e3d568f1e28a1ba3b30d785f2348f7cc44e43a325f9777ef72c8e35a2- Stable URL of this page
https://metraipolis.com/documento/dc_eb28ec98f8b6
How to cite
Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching — arXiv:2608.11030 — arXiv (en), https://arxiv.org/abs/2608.11030 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb28ec98f8b6 (Metraipolis archive dc_eb28ec98f8b6, sha256 6e07c19e3d568f1e28a1ba3b30d785f2348f7cc44e43a325f9777ef72c8e35a2)
BibTeX
@misc{dceb28ec98f8b6,
title = {Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching — arXiv:2608.11030},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11030},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb28ec98f8b6; sha256 6e07c19e3d568f1e28a1ba3b30d785f2348f7cc44e43a325f9777ef72c8e35a2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11030. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CL). Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.11030 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T06:08:50.372Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).