Awesome-LLM4Patents

We will continue to follow up on research related to LLMs for the patent domain and explore further developments in this area. If you are interested in collaborating, please feel free to contact us.

Email: wangqiyao@mail.dlut.edu.cn.

📢 News

• [2024-09-01] Project Beginning.

---

• Papers
  • Survey
  • Patent Model Optimizing
  • Patent Retrieval
  • Patent Generation
    • Patent Writing
    • Long-Context Generation
  • Patent Information Extraction and KG
  • Patent Agents
  • Patents (IP) with Multimodal
  • Evaluation and Dataset
• Repositories

---

Papers

🔥 for papers with >50 citations or repositories with >200 stars.
📖 for papers accepted by reputed conferences/journals.
🙋 for our team's paper.

Survey

• [March 2024] Natural Language Processing in Patents: A Survey. Jiang, Lekang, and Stephan Goetz. Arxiv 2024. [paper]
• [April 2024] A Comprehensive Survey on AI-based Methods for Patents. Homaira Huda Shomee, Zhu Wang, Sathya N. Ravi, Sourav Medya. Arxiv 2024. [paper]

Patent Model Optimizing

• [Sep. 2024] PatentGPT: A Large Language Model for Patent Drafting Using Knowledge-based Fine-tuning Method. Runtao Ren, Jian Ma. Arxiv 2024. [paper]
• [April 2024] PatentGPT: A Large Language Model for Intellectual Property. Zilong Bai, Ruiji Zhang, Linqing Chen, Qijun Cai et.al.. Arxiv 2024. [paper]
• 📖 [May 2024] InstructPatentGPT: Training patent language models to follow instructions with human feedback. Jieh-Sheng Lee. Artif Intell Law 2024. [paper]

Patent Retrieval

• [March 2024] A comparative analysis of embedding models for patent similarity. Grazia Sveva Ascione, Valerio Sterzi. Arxiv 2024. [paper]

Patent Information Extraction and KG

• [March 2024] LLM-based Extraction of Contradictions from Patents. Stefan Trapp, Joachim Warschat. Arxiv 2024. [paper]

Patent Generation

Patent Writing

• 🙋 [Dec. 2024] AutoPatent: A Multi-Agent Framework for Automatic Patent Generation. Qiyao Wang, Shiwen Ni, Huaren Liu, Shule Lu, Guhong Chen, Xi Feng, Chi Wei, Qiang Qu, Hamid Alinejad-Rokny, Yuan Lin, Min Yang. Arxiv 2024. [paper][github]
• [Oct. 2024] Pap2Pat: Towards Automated Paper-to-Patent Drafting using Chunk-based Outline-guided Generation. Valentin Knappich, Simon Razniewski, Anna Hätty, Annemarie Friedrich. Arxiv 2024. [paper]github]
• 📖 [June 2024] Can Large Language Models Generate High-quality Patent Claims? Lekang Jiang, Caiqi Zhang, Pascal A Scherz, Stephan Goetz. Arixv 2024. [paper][github]
• 📖 [Oct. 2023] Creating a Silver Standard for Patent Simplification. Silvia Casola, Alberto Lavelli, Horacio Saggion. SIGIR 2023. [paper][github]
• 📖 [July 2022] PGT: a prompt based generative transformer for the patent domain. Dimitrios Christofidellis, Antonio Berrios Torres, Ashish Dave et.al.. IBM 2022. [paper]

Long-Context Generation

• [Aug. 2024] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs. Yushi Bai, Jiajie Zhang, Xin Lv et.al.. Arxiv 2024. [paper][github][huggingface]
• 📖 [April. 2024] Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models. Yijia Shao, Yucheng Jiang, Theodore A. Kanell. NAACL 2024. [paper]
• [Feb. 2024] LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration. Jun Zhao, Can Zu, Hao Xu. Arxiv 2024. [paper]

Patent Agents

• [Sep. 2024] Towards Automated Patent Workflows: AI-Orchestrated Multi-Agent Framework for Intellectual Property Management and Analysis. Sakhinana Sagar Srinivas, Vijay Sri Vaikunth, Venkataramana Runkana. Arxiv 2024. [paper]
• [Feb. 2024] From PARIS to LE-PARIS: Toward Patent Response Automation with Recommender Systems and Collaborative Large Language Models. Jung-Mei Chu, Hao-Cheng Lo, Jieh Hsiang, Chun-Chieh Cho. Arxiv 2024. [paper]

Patents with Multimodal

• 📖 [Dec. 2024] Large Multimodal Model for Generating Descriptions for Patent Figures. Shreya Shukla, Nakul Sharma, Manish Gupta, Anand Mishra1. [paper][github]. AAAI 2025.
• 📖 [Sep. 2024] IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents. Homaira Huda Shomee, Zhu Wang, Sathya N. Ravi, Sourav Medya. [[paper(https://openreview.net/pdf?id=l0Ydsl10ci)]] [github] Neurips 2024.
• [April 2024] Large Language Model Informed Patent Image Retrieval. Hao-Cheng Lo, Jung-Mei Chu, Jieh Hsiang, Chun-Chieh Cho. Arxiv 2024. [paper]
• 📖 [Sep. 2023] PatFig: Generating Short and Long Captions for Patent Figures. Dana Aubakirova, Kim Gerdes, Lufei Liu. ICCV 2023. [paper][huggingface]

Evaluation and Dataset

• [Feb. 2025] Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art. Hayato Ikoma, Teruko Mitamura. Arxiv 2025. [paper]
• [Sep. 2024] Intelligent Innovation Dataset on Scientific Research Outcomes and Patents. Xinran Wu, Hui Zou, Yidan Xing, Jingjing Qu, Qiongxiu Li, Renxia Xue, Xiaoming Fu. Arxiv 2024. [paper][dataset]
• [July 2024] A Comparative Study of Quality Evaluation Methods for Text Summarization. Huyen Nguyen, Haihua Chen, Lavanya Pobbathi, Junhua Ding. Arxiv 2024. [paper]
• 📖 [June 2024] PatentEval: Understanding Errors in Patent Generation. You Zuo (ALMAnaCH), Kim Gerdes (LISN), Eric Villemonte de La Clergerie (ALMAnaCH), Benoît Sagot (ALMAnaCH). NAACL 2024.[paper]
• 🙋 [June 2024] IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models. Qiyao Wang, Jianguo Huang, Shule Lu et.al. [paper][website][github][huggingface]
• 📖 [Feb. 2024] MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property. Shiwen Ni, Minghuan Tan, Yuelin Bai, ..., Min Yang et.al.. LREC-COLING 2024. [paper][github]
• 📖 [July 2022] The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications. Mirac Suzgun, Luke Melas-Kyriazi, Suproteem K. Sarkar et.al.. Neurips 2022. [paper][website][github][huggingface]

Repositories