PatentEdits: Framing Patent Novelty as Textual Entailment
This addresses a crucial step in patent examination for inventors and examiners, but it is an incremental application of existing methods to a new domain.
The paper tackles the problem of predicting how patent claims should be revised to overcome novelty objections by introducing the PatentEdits dataset with 105K examples and showing that textual entailment evaluation with LLMs effectively predicts which claims remain novel.
A patent must be deemed novel and non-obvious in order to be granted by the US Patent Office (USPTO). If it is not, a US patent examiner will cite the prior work, or prior art, that invalidates the novelty and issue a non-final rejection. Predicting what claims of the invention should change given the prior art is an essential and crucial step in securing invention rights, yet has not been studied before as a learnable task. In this work we introduce the PatentEdits dataset, which contains 105K examples of successful revisions that overcome objections to novelty. We design algorithms to label edits sentence by sentence, then establish how well these edits can be predicted with large language models (LLMs). We demonstrate that evaluating textual entailment between cited references and draft sentences is especially effective in predicting which inventive claims remained unchanged or are novel in relation to prior art.