Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art

2025-02-10

AI Summary

This work addresses the critical challenge of assessing claim novelty in patent examination by introducing, for the first time, a novelty determination task and a dedicated benchmark dataset derived from real-world examination cases. Methodologically, we propose a generative reasoning framework grounded in large language models (LLMs), which jointly models structured patent document understanding and fine-grained semantic alignment between claims and cited prior art. Unlike conventional binary classification approaches, our method outputs both accurate novelty verdicts and human-interpretable natural-language explanations that precisely identify distinguishing technical features. Experimental results demonstrate that the generated explanations significantly enhance human-AI collaborative examination efficiency. Our approach establishes a new paradigm for AI-augmented patent examination and provides empirical validation for explainable, LLM-based novelty assessment.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Assessing the novelty of patent claims is a critical yet challenging task traditionally performed by patent examiners. While advancements in NLP have enabled progress in various patent-related tasks, novelty assessment remains unexplored. This paper introduces a novel challenge by evaluating the ability of large language models (LLMs) to assess patent novelty by comparing claims with cited prior art documents, following the process similar to that of patent examiners done. We present the first dataset specifically designed for novelty evaluation, derived from real patent examination cases, and analyze the capabilities of LLMs to address this task. Our study reveals that while classification models struggle to effectively assess novelty, generative models make predictions with a reasonable level of accuracy, and their explanations are accurate enough to understand the relationship between the target patent and prior art. These findings demonstrate the potential of LLMs to assist in patent evaluation, reducing the workload for both examiners and applicants. Our contributions highlight the limitations of current models and provide a foundation for improving AI-driven patent analysis through advanced models and refined datasets.

Problem

• AI assesses patent novelty
• LLMs compare claims with prior art
• Generative models improve patent evaluation accuracy

Innovation

• LLMs assess patent novelty
• Generative models predict accurately
• Dataset for novelty evaluation