# Benchmarking Patent Drafting from Inventor-Style Disclosures

arXiv: https://arxiv.org/abs/2608.21249 · HTML: https://mlsanity.com/paper/2608.21249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Patent Claim Generation by Fine-Tuning OpenAI GPT-2](https://mlsanity.com/paper/1907.02052/) (2019)
- [Natural Language Processing in the Patent Domain: A Survey](https://mlsanity.com/paper/2403.04105/) (2024)
- [Can Large Language Models Generate High-quality Patent Claims?](https://mlsanity.com/paper/2406.19465/) (2024)
- [PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims](https://mlsanity.com/paper/2505.19345/) (2025)
- [Pap2Pat: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairs](https://mlsanity.com/paper/2410.07009/) (2024)
- [Towards Better Evaluation for Generated Patent Claims](https://mlsanity.com/paper/2505.11095/) (2025)
- [PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures](https://mlsanity.com/paper/2501.15074/) (2025)
- [Enriching Patent Claim Generation with European Patent Dataset](https://mlsanity.com/paper/2505.12568/) (2025)
- [PatentMind: A Multi-Aspect Reasoning Graph for Patent Similarity Evaluation](https://mlsanity.com/paper/2505.19347/) (2025)
- [Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification](https://mlsanity.com/paper/2510.05431/) (2025)
- [PatentEval: Understanding Errors in Patent Generation](https://mlsanity.com/paper/2406.06589/) (2024)
- [AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification](https://mlsanity.com/paper/2509.19640/) (2025)
- [Pat-DEVAL: Chain-of-Legal-Thought Evaluation for Patent Description](https://mlsanity.com/paper/2601.00166/) (2026)
- [Reasoning for Hierarchical Text Classification: The Case of Patents](https://mlsanity.com/paper/2510.07167/) (2025)
- [PatentVision: A multimodal method for drafting patent applications](https://mlsanity.com/paper/2510.09762/) (2025)
- [Adaptive Cost-Efficient Evaluation for Reliable Patent Claim Generation](https://mlsanity.com/paper/2604.04295/) (2026)
- [Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval](https://mlsanity.com/paper/2605.02392/) (2026)
- [When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation](https://mlsanity.com/paper/2607.10480/) (2026)
- [Pointer-Augmented Autoregressive Generation of Patent Claims with Joint Topology and Content Decoding](https://mlsanity.com/paper/2607.24040/) (2026)

## Abstract (arXiv)

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.