Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval

TL;DR

This paper introduces FiNE-Patents, a dataset and method for fine-grained, feature-level patent novelty prediction using large language models, improving interpretability and robustness over traditional binary classification.

Contribution

The work presents a new dataset and a shift from claim-level binary classification to feature-level passage retrieval and reasoning for patent novelty assessment.

Findings

LLMs outperform embedding-based baselines in passage retrieval.

LLMs are more robust against spurious correlations in novelty prediction.

The dataset and code are publicly released for further research.

Abstract

Novelty assessment is a critical yet complex task in the examination process for patent acceptance, requiring examiners to determine whether an invention is disclosed in a prior art document. The process involves intricate matching between specific features of a patent claim and passages in the prior art. While prior work has approached novelty prediction primarily as a binary classification task at the claim level, we argue that this formulation is susceptible to spurious correlations and lacks the granularity required for practical application. In this work, we introduce FiNE-Patents (Fine-grained Novelty Examination of Patents), a novel dataset comprising 3,658 first patent claims annotated with fine-grained, feature-level prior art references extracted from European Search Opinion (ESOP) documents. We propose shifting the evaluation paradigm from simple binary classification to a joint retrieval and abstract reasoning task at the feature level, requiring models to identify specific passages from a prior art document that disclose individual claim features, and to identify which features of a claim make it novel. We implement and evaluate LLM-based workflows that decompose claims into features, analyze each feature against prior art, and finally derive a claim-level novelty prediction. Our experiments demonstrate that these workflows outperform embedding-based baselines on passage retrieval and novel feature identification. Furthermore, we show that unlike trained classifiers, LLMs are robust against spurious correlations present in the claim-level novelty classification task. We release the dataset and code to foster further research into transparent and granular patent analysis.