A new patent novelty benchmark from real examiner rejections shows large language models can classify novelty at about 62% accuracy, while smaller classification models perform at chance.
Google patents public datasets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art
A new patent novelty benchmark from real examiner rejections shows large language models can classify novelty at about 62% accuracy, while smaller classification models perform at chance.