Benchmarking Patent Drafting from Inventor-Style Disclosures

• URL: http://arxiv.org/abs/2608.21249v1
• Date: Fri, 21 Aug 2026 16:00:52 GMT
• Title: Benchmarking Patent Drafting from Inventor-Style Disclosures
• Abstract summary: Dis2Pat is a disclosure-to-patent dataset that reflects realistic patenting.<n>Patent-MAF is a multi-agent framework for locally deployable patent drafting.
• Score: 3.536605202672355
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate the core challenge of real-world patent drafting: generating a complete and legally coherent patent application directly from early-stage invention materials. Prior work predominantly assumes later-stage, highly structured, or already legalistic inputs. However, real patenting workflows begin with informal, de-legalized disclosures authored by inventors. To bridge the gap, we introduce Dis2Pat, a disclosure-to-patent dataset that reflects realistic patenting workflows by requiring the generation of complete patent applications directly from inventor-style, de-legalized disclosures. Given the inherent difficulty of long-form, legally constrained patent drafting and the strong privacy requirements, we further propose a strong baseline named Patent-MAF. It is a multi-agent framework for locally deployable patent drafting. Benchmark results reveal that current LLMs exhibit limitations in patent drafting, while Patent-MAF provides a strong baseline that consistently outperforms evaluated open-source models and remains competitive with large closed-source models.

Related papers

• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice [67.71760070255425]
  We introduce PLawBench, a practical benchmark for evaluating large language models (LLMs) in legal practice scenarios.<n>PLawBench comprises 850 questions across 13 practical legal scenarios, with each question accompanied by expert-designed evaluation rubrics.<n>Using an LLM-based evaluator aligned with human expert judgments, we evaluate 10 state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2026-01-23T11:36:10Z)
• PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination [44.74519851862391]
  We build PANORAMA, a dataset of 8,143 U.S. patent examination records.<n>We decompose the trails into sequential benchmarks that emulate patent professionals' patent review processes.<n>We argue that advancing NLP, including LLMs, in the patent domain requires a deeper understanding of real-world patent examination.
  arXiv  Detail & Related papers  (2025-10-25T03:24:13Z)
• Patentformer: A demonstration of AI-assisted automated patent drafting [4.1765120028423]
  Patent attorneys must possess both legal acumen and technical understanding of an invention to craft patent applications in a formal legal writing style.<n>Patentformer is an AI-powered automated patent drafting platform designed to support patent attorneys by rapidly producing high-quality patent applications adhering to legal writing standards.
  arXiv  Detail & Related papers  (2025-10-10T18:00:03Z)
• ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation [56.79698529022327]
  Legal claims refer to the plaintiff's demands in a case and are essential to guiding judicial reasoning and case resolution.<n>This paper explores the problem of legal claim generation based on the given case's facts.<n>We construct ClaimGen-CN, the first dataset for Chinese legal claim generation task.
  arXiv  Detail & Related papers  (2025-08-24T07:19:25Z)
• Enriching Patent Claim Generation with European Patent Dataset [2.0270237738043906]
  We introduce EPD, a European patent dataset. EPD presents rich textual data and structured metadata to support patent-related tasks, including claim generation.<n>EPD fills a critical gap by providing a benchmark for European patents to enable more comprehensive evaluation.<n>Experiments show that LLMs fine-tuned on EPD significantly outperform those trained on previous datasets and even GPT-4o in claim quality and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-05-18T23:04:49Z)
• Towards Better Evaluation for Generated Patent Claims [0.0]
  We introduce Patent-CE, the first comprehensive benchmark for evaluating patent claims.<n>We also propose PatClaimEval, a novel multi-dimensional evaluation method specifically designed for patent claims.<n>This research provides the groundwork for more accurate evaluations of automated patent claim generation systems.
  arXiv  Detail & Related papers  (2025-05-16T10:27:16Z)
• Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art [5.655276956391884]
  This paper introduces a novel challenge by evaluating the ability of large language models (LLMs) to assess patent novelty.<n>We present the first dataset specifically designed for novelty evaluation, derived from real patent examination cases.<n>Our study reveals that while classification models struggle to effectively assess novelty, generative models make predictions with a reasonable level of accuracy.
  arXiv  Detail & Related papers  (2025-02-10T10:09:29Z)
• PatentEdits: Framing Patent Novelty as Textual Entailment [62.8514393375952]
  We introduce the PatentEdits dataset, which contains 105K examples of successful revisions. We design algorithms to label edits sentence by sentence, then establish how well these edits can be predicted with large language models. 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.
  arXiv  Detail & Related papers  (2024-11-20T17:23:40Z)
• Structural Representation Learning and Disentanglement for Evidential Chinese Patent Approval Prediction [19.287231890434718]
  This paper presents the pioneering effort on this task using a retrieval-based classification approach. We propose a novel framework called DiSPat, which focuses on structural representation learning and disentanglement. Our framework surpasses state-of-the-art baselines on patent approval prediction, while also exhibiting enhanced evidentiality.
  arXiv  Detail & Related papers  (2024-08-23T05:44:16Z)
• Unveiling Black-boxes: Explainable Deep Learning Models for Patent Classification [48.5140223214582]
  State-of-the-art methods for multi-label patent classification rely on deep opaque neural networks (DNNs) We propose a novel deep explainable patent classification framework by introducing layer-wise relevance propagation (LRP) Considering the relevance score, we then generate explanations by visualizing relevant words for the predicted patent class.
  arXiv  Detail & Related papers  (2023-10-31T14:11:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.