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

• URL: http://arxiv.org/abs/2410.07009v2
• Date: Thu, 06 Mar 2025 08:51:05 GMT
• Title: Pap2Pat: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairs
• Authors: Valentin Knappich, Simon Razniewski, Anna Hätty, Annemarie Friedrich,
• Abstract summary: We build PAP2PAT, an open benchmark for patent drafting consisting of 1.8k patent-paper pairs describing the same inventions.<n>Our 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.
• Score: 13.242188189150987
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• AutoPatent: A Multi-Agent Framework for Automatic Patent Generation [16.862811929856313]
  We introduce a novel and practical task known as Draft2Patent, along with its corresponding D2P benchmark, which challenges Large Language Models to generate full-length patents averaging 17K tokens based on initial drafts. We propose a multi-agent framework called AutoPatent which leverages the LLM-based planner agent, writer agents, and examiner agent with PGTree and RRAG to generate lengthy, intricate, and high-quality complete patent documents.
  arXiv  Detail & Related papers  (2024-12-13T02:27:34Z)
• 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)
• BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
  BRIEF (Bridging Retrieval and Inference through Evidence Fusion) is a lightweight approach that performs query-aware multi-hop reasoning. Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
  arXiv  Detail & Related papers  (2024-10-20T04:24:16Z)
• O1 Replication Journey: A Strategic Progress Report -- Part 1 [52.062216849476776]
  This paper introduces a pioneering approach to artificial intelligence research, embodied in our O1 Replication Journey. Our methodology addresses critical challenges in modern AI research, including the insularity of prolonged team-based projects. We propose the journey learning paradigm, which encourages models to learn not just shortcuts, but the complete exploration process.
  arXiv  Detail & Related papers  (2024-10-08T15:13:01Z)
• PATopics: An automatic framework to extract useful information from pharmaceutical patents documents [4.340983107526238]
  PATopics is a framework specially designed to extract relevant information for Pharmaceutical patents. We extensively analyzed the framework using 4,832 pharmaceutical patents concerning 809 molecules patented by 478 companies.
  arXiv  Detail & Related papers  (2024-08-12T19:18:51Z)
• Natural Language Processing in Patents: A Survey [0.0]
  Patents, encapsulating crucial technical and legal information, present a rich domain for natural language processing (NLP) applications. As NLP technologies evolve, large language models (LLMs) have demonstrated outstanding capabilities in general text processing and generation tasks. This paper aims to equip NLP researchers with the essential knowledge to navigate this complex domain efficiently.
  arXiv  Detail & Related papers  (2024-03-06T23:17:16Z)
• PaECTER: Patent-level Representation Learning using Citation-informed Transformers [0.16785092703248325]
  PaECTER is a publicly available, open-source document-level encoder specific for patents. We fine-tune BERT for Patents with examiner-added citation information to generate numerical representations for patent documents. PaECTER performs better in similarity tasks than current state-of-the-art models used in the patent domain.
  arXiv  Detail & Related papers  (2024-02-29T18:09:03Z)
• LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation [74.7163199054881]
  Large Language Models (LLMs) have demonstrated their capability in context understanding, logic reasoning and answer generation. We present a systematic study on the application of LLMs in the EDA field. We highlight the future research direction, focusing on applying LLMs in logic synthesis, physical design, multi-modal feature extraction and alignment of circuits.
  arXiv  Detail & Related papers  (2023-12-28T15:09:14Z)
• Leveraging Large Language Models to Improve REST API Testing [51.284096009803406]
  RESTGPT takes as input an API specification, extracts machine-interpretable rules, and generates example parameter values from natural-language descriptions in the specification. Our evaluations indicate that RESTGPT outperforms existing techniques in both rule extraction and value generation.
  arXiv  Detail & Related papers  (2023-12-01T19:53:23Z)
• 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)
• PaperCard for Reporting Machine Assistance in Academic Writing [48.33722012818687]
  ChatGPT, a question-answering system released by OpenAI in November 2022, has demonstrated a range of capabilities that could be utilised in producing academic papers. This raises critical questions surrounding the concept of authorship in academia. We propose a framework we name "PaperCard", a documentation for human authors to transparently declare the use of AI in their writing process.
  arXiv  Detail & Related papers  (2023-10-07T14:28:04Z)
• The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications [8.110699646062384]
  We introduce the Harvard USPTO Patent dataset (HUPD) With more than 4.5 million patent documents, HUPD is two to three times larger than comparable corpora. By providing each application's metadata along with all of its text fields, the dataset enables researchers to perform new sets of NLP tasks.
  arXiv  Detail & Related papers  (2022-07-08T17:57:15Z)
• A Survey on Sentence Embedding Models Performance for Patent Analysis [0.0]
  We propose a standard library and dataset for assessing the accuracy of embeddings models based on PatentSBERTa approach. Results show PatentSBERTa, Bert-for-patents, and TF-IDF Weighted Word Embeddings have the best accuracy for computing sentence embeddings at the subclass level.
  arXiv  Detail & Related papers  (2022-04-28T12:04:42Z)
• Context-Tuning: Learning Contextualized Prompts for Natural Language Generation [52.835877179365525]
  We propose a novel continuous prompting approach, called Context-Tuning, to fine-tuning PLMs for natural language generation. Firstly, the prompts are derived based on the input text, so that they can elicit useful knowledge from PLMs for generation. Secondly, to further enhance the relevance of the generated text to the inputs, we utilize continuous inverse prompting to refine the process of natural language generation.
  arXiv  Detail & Related papers  (2022-01-21T12:35:28Z)
• Patent Sentiment Analysis to Highlight Patent Paragraphs [0.0]
  Given a patent document, identifying distinct semantic annotations is an interesting research aspect. In the process of manual patent analysis, to attain better readability, recognising the semantic information by marking paragraphs is in practice. This work assist patent practitioners in highlighting semantic information automatically and aid to create a sustainable and efficient patent analysis using the aptitude of Machine Learning.
  arXiv  Detail & Related papers  (2021-11-06T13:28:29Z)

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.