•  
  •  
 

Abstract

One of the most challenging aspects for inventors seeking to obtain a patent is conducting an effective preliminary prior art search. The process requires specialized skills and experience to assess the relevant information that many novice inventors do not possess. However, artificial intelligence (AI) tools and Large Language Models (LLMs) offer potential new ways of accessing legal and technical expertise. This study surveys five popular publicly available LLMs ability to aid in conducting a preliminary prior art search. A list of best practices and strategies for using AI tools to conduct preliminary patent searches are outlined at the conclusion of the article.

The authors evaluate the applicability of publicly available LLMs, Copilot, ChatGPT, Claude, Gemini, and Perplexity, by assessing their capabilities for conducting prior art searches. This study also explores the effectiveness of available features such as image or link interpretation, patent vs non-patent literature retrieval, and CPC classification support. Furthermore, this study addresses qualitative metrics relevant to prior art searches, such as consistency and accuracy of AI output, degree of overlap across models, and ability to present conceptually relevant prior art from adjacent fields. A comparative analysis of publicly available platforms illustrates the potential benefit to the general public seeking patent information. By addressing the strengths and weaknesses of publicly available LLM’s, this study demonstrates that consistency, reliability, and human verification are necessary when conducting a preliminary prior art search. This research aims to build a framework to allow novice inventors to use largely available generative AI tools to help streamline their preliminary prior art search process.

References

Ali, A., Tufail, A., De Silva, L. C., & Abas, P. E. (2024, September 26). Innovating patent retrieval: A comprehensive review of techniques, trends, and challenges in prior art searches. Applied System Innovation, 7(5), 91. https://doi.org/10.3390/asi7050091

Al-Sinani, H. S., & Mitchell, C. J. (2025, October). AI-generated papers and manipulation of academic metrics: A case study. 2025 IEEE 8th Congress on Information Science and Technology (CiSt) (pp. 583-588). Marrakech, Morocco. DOI: 0.1109/CiSt65886.2025.11224292

Amazon. (n.d.) AboveTEK Laptop Sleeve Case for 13-14 inch MacBook Air/Pro, Slim Laptop Case with Stand, Ergonomic Wrist Rest & Mouse Pad, Waterproof Anti-Scratch Leather Bag for 13-14 Surface HP, Grey. https://a.co/d/0885OBMs

Anthropic. (n.d.). How do usage and length limits work? https://support.claude.com/en/articles/11647753-how-do-usage-and-length-limits-work

Athaluri, S., Manthena, S., Kesapragada. V., et al. (2023, April 11). Exploring the Boundaries of Reality: Investigating the Phenomenon of Artificial Intelligence Hallucination in Scientific Writing Through ChatGPT References. Cureus, 15(4): e37432. DOI: 10.7759/cureus.37432

Bergeaud, A., Emer, L., Lippi, M., Mina, A., & others. (2026, January 30). Large language models for patent classification. arXiv. https://arxiv.org/abs/2601.23200 Bui, L. V. (2025, March). Advancing patent law with generative AI: Human‑in‑the‑loop systems for AI‑assisted drafting, prior art search, and multimodal IP protection. World Patent Information, 80, Article 102341. https://doi.org/10.1016/j.wpi.2025.102341

ClaudeLog. (n.d.). Is Claude AI free? https://claudelog.com/faqs/claude-ai-is-free/

Chikkamath, R., Andersson, L., & Endres, M. (2026, March). Rethinking patent retrieval with language models: Toward scalable and efficient search. World Patent Information, 84, 102433. https://doi.org/10.1016/j.wpi.2026.102433

DAIR.AI. (2025, December 28). Prompt engineering guide. https://www.promptingguide.ai/

DeltaHub. (n.d.). FORMO 3‑in‑1 laptop bag [Product page]. https://deltahub.io/products/formo-3-in-1-laptop-bag

ding_fow. (2025, July). Fatal: The Gemini series (especially DeepResearch) hallucinates very severely in patent retrieval tasks [Online forum post]. Google AI Developers Forum. https://discuss.ai.google.dev/t/fatal-the-gemini-series-especially-deepresearch-hallucinates-very-severely-in-patent-retrieval-tasks/93108

DrugPatentWatch. (2026, March 12). The future of patent intelligence tools: How AI is revolutionizing the landscape. https://www.drugpatentwatch.com/blog/the-future-of-patent-intelligence-tools-how-ai-is-revolutionizing-the-landscape/

European Patent Office. (n.d.). CPC essentials I – Part B [PDF]. https://link.epo.org/cpc/CPC_Essentials_I_PartB.pdf

Fritz AI. (2025, September 19). Claude AI free vs Pro: Which is right for you? https://fritz.ai/claude-ai-free-vs-pro/

Genin, B., Gorbunov, A., Zolkin, D., & Nekrasov, I. (2026, January 5). AI prior art search: Semantic clusters and evaluation infrastructure. arXiv. https://doi.org/10.48550/arXiv.2512.18384

Gonzalez, P. F. (2010, October 26). Combined laptop case and laptop stand (U.S. Patent No. US7819247B2). U.S. Patent and Trademark Office.

Hansen P, Järvelin A., & Järvelin A. (2013). Exploring manual and automatic query formulation in patent IR: Initial query construction and query generation process. Journal of Documentation, 69(6), 873–898. https://doi.org/10.57809/2025.4.2.13.1

Haque, R., Rose, S., & DeSetto, N.. (2024). The non-obvious razor & generative ai. North Carolina Journal of Law & Technology, 25(3), 399-446. https://scholarship.law.unc.edu/ncjolt/vol25/iss3/3

Helmers, L., Horn, F., Biegler, F., Oppermann, T., & Müller, K.-R. (2019, March 4). Automating the search for a patent’s prior art with a full text similarity search. PLOS ONE, 14(3), e0212103. https://doi.org/10.1371/journal.pone.0212103

Judy, R. (2020, July 7). Faraday bag with magnetic closure system (U.S. Patent No. US10,709,044B1). U.S. Patent and Trademark Office.

Kalinichenko, A. L., & Willoughby, K. W. (2025, September). The effective use of artificial intelligence in patent searches. World Patent Information, 82, Article 102387. https://doi.org/10.1016/j.wpi.2025.102387

Kamateri, E., Salampasis, M., & Perez-Molina, E. (2024, September). Will AI solve the patent classification problem? World Patent Information, 75, 102460. https://www.sciencedirect.com/science/article/pii/S0172219024000346

Krishna, A., Jin, Y., Song, Y., & Youssef, A. (2019, November 14). Query expansion for patent searching using word embedding and professional crowdsourcing. arXiv. https://doi.org/10.48550/arXiv.1911.11069

Kim, S. K. (2009, June 25). Portable laptop stand (U.S. Patent Application No. US20090159763A1). U.S. Patent and Trademark Office.

Kusetogullari, A., Kusetogullari, H., Andersson, M., & Gorschek, T. (2025, May 8). GenAI in entrepreneurship: A systematic review of generative artificial intelligence in entrepreneurship research: Current issues and future directions. arXiv. https://doi.org/10.48550/arXiv.2505.05523

Lin, Z. (2025). Beyond principlism: Practical strategies for ethical AI use in research practices. AI and Ethics, 5(6), 2719–2731. https://doi.org/10.1007/s43681-024-00585-5

Magesh, V., Bhatia, N., Henderson, P., Ho, D. E., et al.. (2025). Hallucination‑free? Assessing the reliability of leading AI legal research tools. Journal of Empirical Legal Studies, 22(2), 385–436. https://doi.org/10.1111/jels.12413

MOFT. (n.d.). MOFT stand adhesive [Product page]. https://www.moft.us/products/moft-stand-adhesive

Park, S., Kim, G., & Lee, S. (2026). Evaluating the value of LLMs in patent‑based technology intelligence: Toward increasing efficiency and reducing expert dependency. Technological Forecasting and Social Change, 222, Article 124375. https://doi.org/10.1016/j.techfore.2025.124375

Patent and Trademark Resource Center Association. (2026). About PTRCA. https://ptrca.org/ptdla/

Pochetniy, V. A. (2025). Integrating generative AI for technological trend analysis and patent research automation. Technoeconomics, 4(2), 4–20. https://doi.org/10.57809/2025.4.2.13.1

QuantumZeitgeist. (2026, February 3). Large language models show promise for USPTO 70k patent classification. https://quantumzeitgeist.com/classification-models-large-language-promise-uspto-70k/

Ren, R., Ma, J., & Luo, J. (2025, May). Large language model for patent concept generation. Advanced Engineering Informatics, 65, 103301. https://doi.org/10.1016/j.aei.2025.103301

Renuk9390. (2024). ChatGPT vs. Google Gemini: Assessing AI frontiers for patent prior art search [Computer software]. GitHub. https://github.com/Renuk9390/ChatGPTvsGoogleGemini

Resnik, D. B., & Hosseini, M. (2025, May 27). The ethics of using artificial intelligence in scientific research: new guidance needed for a new tool. AI and ethics, 5(2), 1499–1521. https://doi.org/10.1007/s43681-024-00493-8

Romani, B. (2021, September 28). What is IMRaD? IMRaD format in simple terms. Medium. https://medium.com/@bizhanrom/what-is-imrad-imrad-format-in-simple-terms-5431bde724d

Shah, S. V. (2024, August 13). Accuracy, consistency, and hallucination of large language models when analyzing unstructured clinical notes in electronic medical records. JAMA Network Open, 7(7), e2422301. https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2822301

Shalaby, W., & Zadrozny, W. (2019, January 14). Patent retrieval: A literature review. Knowledge and Information Systems, 61(3), 1261–1290. https://doi.org/10.1007/s10115-018-1322-7

Sherriff, G. (2024). How to read a patent: A survey of the textual characteristics of patent documents and strategies for comprehension. Journal of the Patent and Trademark Resource Center Association, 34(1), Article 3. https://open.clemson.edu/jptrca/vol34/iss1/3/

Shomee, H. H., Wang, Z., Ravi, S. N., & Medya, S. (2025, July). A survey on patent analysis: From NLP to multimodal AI. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (8383–8406). Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.419/

Staudinger, M., Kusa, W., Piroi, F., Lipani, A., Hanbury, A., & Azzopardi, L. (2024, December 8). A reproducibility and generalizability study of large language models for query generation. In Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (pp. 186–196). ACM. https://doi.org/10.1145/3673791.3698432

Team PQAI. (2025, August 4). ChatGPT for patent search: How PQAI integration changes the game. https://projectpq.ai/chatgpt-for-patent-search-semantic-search-integration/

Tomková, M., Čorejová, A., & Horniká, K. (2026). Patent searches in the university environment: New challenges and approaches. Transportation Research Procedia, 93, 1182-1187. https://www.sciencedirect.com/science/article/pii/S2352146525009469

United States Patent and Trademark Office. (2024b). Basics of prior art searching [PDF]. https://www.uspto.gov/sites/default/files/documents/Basics-of-Prior-Art-Searching.pdf

United States Patent and Trademark Office. (2024c, April 11). Guidance on use of artificial intelligence‑based tools in practice before the United States Patent and Trademark Office. Federal Register, 89(71), 25871–25881. https://www.federalregister.gov/documents/2024/04/11/2024-07629/guidance-on-use-of-artificial-intelligence-based-tools-in-practice-before-the-united-states-patent

United States Patent and Trademark Office. (2024a, February 4). Patent and Trademark Resource Centers. https://www.uspto.gov/learning-and-resources/patent-trademark-resource-centers

Villa, A. M., & Wirz, M. (2022, March). A sequential patent search approach combining semantics and artificial intelligence to identify initial state‑of‑the‑art documents. World Patent Information, 68, 102096. https://doi.org/10.1016/j.wpi.2022.102096

Wang, R. Y., & Strong, D. M. (1996). Beyond accuracy: What data quality means to data consumers. Journal of Management Information Systems, 12(4), 5–33. https://doi.org/10.1080/07421222.1996.11518099

World Intellectual Property Organization. (2024). Patent landscape report: Generative artificial intelligence (GenAI) – Appendices. https://www.wipo.int/web-publications/patent-landscape-report-generative-artificial-intelligence-genai/en/appendices.html

Yang, J., Jin, H., Tang, R., Han, X, Feng, Q., & Jiang, H. (2024, April 27). Harnessing the power of LLMs in practice: A survey on ChatGPT and beyond. ACM Transactions on Knowledge Discovery from Data, 18(6), Article 121. https://doi.org/10.1145/3649506

Zwicky, D. (2019) Thoughts on patents and information literacy, Journal of the Patent and Trademark Resource Center Association: 29(1). https://open.clemson.edu/jptrca/vol29/iss1/1

Download

Share

COinS