# Pap2Pat: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairs

arXiv: https://arxiv.org/abs/2410.07009 · HTML: https://mlsanity.com/paper/2410.07009/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 71 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation](https://mlsanity.com/paper/1904.02357/) (2019)
- [Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective](https://mlsanity.com/paper/2310.10226/) (2023)
- [DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence](https://mlsanity.com/paper/2201.11176/) (2022)
- [Fast and Accurate Factual Inconsistency Detection Over Long Documents](https://mlsanity.com/paper/2310.13189/) (2023)
- [Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries](https://mlsanity.com/paper/2010.07074/) (2020)
- [InstructPatentGPT: Training patent language models to follow instructions with human feedback](https://mlsanity.com/paper/2406.16897/) (2024)
- [Patent Retrieval: A Literature Review](https://mlsanity.com/paper/1701.00324/) (2017)
- [Hyperparameter Optimization for Large Language Model Instruction-Tuning](https://mlsanity.com/paper/2312.00949/) (2023)
- [Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models](https://mlsanity.com/paper/2404.13919/) (2024)
- [StyloMetrix: An Open-Source Multilingual Tool for Representing Stylometric Vectors](https://mlsanity.com/paper/2309.12810/) (2023)
- [SemOpenAlex: The Scientific Landscape in 26 Billion RDF Triples](https://mlsanity.com/paper/2308.03671/) (2023)
- [A Survey on Patent Analysis: From NLP to Multimodal AI](https://mlsanity.com/paper/2404.08668/) (2024)
- [Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events](https://mlsanity.com/paper/2101.00822/) (2021)
- [Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control](https://mlsanity.com/paper/2305.14459/) (2023)
- [Hierarchical Text Generation using an Outline](https://mlsanity.com/paper/1810.08802/) (2018)

## Built on by (most cited first, 8 of 8)

- [AutoPatent: A Multi-Agent Framework for Automatic Patent Generation](https://mlsanity.com/paper/2412.09796/) (2024)
- [Pat-DEVAL: Chain-of-Legal-Thought Evaluation for Patent Description](https://mlsanity.com/paper/2601.00166/) (2026)
- [FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions](https://mlsanity.com/paper/2601.02589/) (2026)
- [Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval](https://mlsanity.com/paper/2605.02392/) (2026)
- [Pointer-Augmented Autoregressive Generation of Patent Claims with Joint Topology and Content Decoding](https://mlsanity.com/paper/2607.24040/) (2026)
- [PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination](https://mlsanity.com/paper/2605.03571/) (2026)
- [Benchmarking Patent Drafting from Inventor-Style Disclosures](https://mlsanity.com/paper/2608.21249/) (2026)
- [LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting](https://mlsanity.com/paper/2609.30943/) (2026)

## Abstract (arXiv)

Dealing with long and highly complex technical text is a challenge for Large Language Models (LLMs), which still have to unfold their potential in supporting expensive and timeintensive processes like patent drafting. Within patents, the description constitutes more than 90% of the document on average. Yet, its automatic generation remains understudied. When drafting patent applications, patent attorneys typically receive invention reports (IRs), which are usually confidential, hindering research on LLM-supported patent drafting. Often, prepublication research papers serve as IRs. We leverage this duality to build PAP2PAT, an open and realistic benchmark for patent drafting consisting of 1.8k patent-paper pairs describing the same inventions. To address the complex longdocument patent generation task, we propose chunk-based outline-guided generation using the research paper as invention specification. Our extensive evaluation using PAP2PAT and a human case study show that LLMs can effectively leverage information from the paper, but still struggle to provide the necessary level of detail. Fine-tuning leads to more patent-style language, but also to more hallucination. We release our data and code https://github.com/boschresearch/Pap2Pat.