ClaimBrush: A Novel Framework for Automated Patent Claim Refinement Based on Large Language Models

TL;DR

This paper introduces ClaimBrush, a framework utilizing large language models and examiner preference data to automatically refine patent claims, improving accuracy over baseline methods.

Contribution

The paper presents a new dataset, a fine-tuned large language model, and a preference optimization approach for automated patent claim refinement.

Findings

The rewriting model outperforms heuristic baselines and zero-shot models.

Preference optimization enhances claim refinement performance.

Constructed a large dataset from patent examination cases.

Abstract

Automatic refinement of patent claims in patent applications is crucial from the perspective of intellectual property strategy. In this paper, we propose ClaimBrush, a novel framework for automated patent claim refinement that includes a dataset and a rewriting model. We constructed a dataset for training and evaluating patent claim rewriting models by collecting a large number of actual patent claim rewriting cases from the patent examination process. Using the constructed dataset, we built an automatic patent claim rewriting model by fine-tuning a large language model. Furthermore, we enhanced the performance of the automatic patent claim rewriting model by applying preference optimization based on a prediction model of patent examiners' Office Actions. The experimental results showed that our proposed rewriting model outperformed heuristic baselines and zero-shot learning in state-of-the-art large language models. Moreover, preference optimization based on patent examiners' preferences boosted the performance of patent claim refinement.