InstructPatentGPT: Training patent language models to follow instructions with human feedback
- URL: http://arxiv.org/abs/2406.16897v1
- Date: Sat, 25 May 2024 11:48:50 GMT
- Title: InstructPatentGPT: Training patent language models to follow instructions with human feedback
- Authors: Jieh-Sheng Lee,
- Abstract summary: This research aims to increase the likelihood for a language model to generate patent claims that have a higher chance of being granted.
To showcase the controllability of the language model, the system learns from granted patents and pre-grant applications with different rewards.
- Score: 0.9790236766474201
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this research, patent prosecution is conceptualized as a system of reinforcement learning from human feedback. The objective of the system is to increase the likelihood for a language model to generate patent claims that have a higher chance of being granted. To showcase the controllability of the language model, the system learns from granted patents and pre-grant applications with different rewards. The status of "granted" and "pre-grant" are perceived as labeled human feedback implicitly. In addition, specific to patent drafting, the experiments in this research demonstrate the model's capability to learn from adjusting claim length and inclusion of limiting terms for narrowing claim scope. As proof of concept, the experiments focus on claim ones only and the training data originates from a patent dataset tailored specifically for artificial intelligence. Although the available human feedback in patent prosecution are limited and the quality of generated patent text requires improvement, the experiments following the 3-stage reinforcement learning from human feedback have demonstrated that generative language models are capable of reflecting the human feedback or intent in patent prosecution. To enhance the usability of language models, the implementation in this research utilizes modern techniques that enable execution on a single consumer-grade GPU. The demonstrated proof of concept, which reduces hardware requirements, will prove valuable in the future as more human feedback in patent prosecution become available for broader use, either within patent offices or in the public domain.
Related papers
- Early screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model [4.779196219827507]
We propose an interpretable machine learning approach to predicting future citation counts from patent texts.
A case study of 35,376 pharmaceutical patents demonstrates the effectiveness of our approach.
It is expected that the proposed approach will enhance expert-machine collaboration in identifying breakthrough technologies.
arXiv Detail & Related papers (2024-07-24T02:17:10Z) - Evaluating Copyright Takedown Methods for Language Models [100.38129820325497]
Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material.
This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs.
We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches.
arXiv Detail & Related papers (2024-06-26T18:09:46Z) - PatentEval: Understanding Errors in Patent Generation [9.981773213952994]
We introduce a comprehensive error typology specifically designed for evaluating two distinct tasks in machine-generated patent texts.
We have also developed a benchmark, PatentEval, for systematically assessing language models in this context.
arXiv Detail & Related papers (2024-06-05T13:55:27Z) - Artificial Intelligence Exploring the Patent Field [0.0]
Advanced language-processing and machine-learning techniques promise massive efficiency improvements in the field of patent and technical knowledge management.
This paper presents a systematic overview of patent-related tasks and popular methodologies with a special focus on evolving and promising techniques.
The paper introduces fundamental aspects of patents and patent-related data that affect technology that wants to explore or manage them.
arXiv Detail & Related papers (2024-03-06T23:17:16Z) - Language Models: A Guide for the Perplexed [51.88841610098437]
This tutorial aims to help narrow the gap between those who study language models and those who are intrigued and want to learn more.
We offer a scientific viewpoint that focuses on questions amenable to study through experimentation.
We situate language models as they are today in the context of the research that led to their development.
arXiv Detail & Related papers (2023-11-29T01:19:02Z) - 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) - Exploration with Principles for Diverse AI Supervision [88.61687950039662]
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI.
While this generative AI approach has produced impressive results, it heavily leans on human supervision.
This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation.
We propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data.
arXiv Detail & Related papers (2023-10-13T07:03:39Z) - Evaluating Generative Patent Language Models [1.8275108630751844]
This manuscript aims to build generative language models in the patent domain.
The perspective is to measure the ratio of keystrokes that can be saved by autocompletion.
The largest model built in this manuscript is 6B, which is state-of-the-art in the patent domain.
arXiv Detail & Related papers (2022-06-23T08:58:05Z) - 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) - Explain, Edit, and Understand: Rethinking User Study Design for
Evaluating Model Explanations [97.91630330328815]
We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews.
We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
arXiv Detail & Related papers (2021-12-17T18:29:56Z) - A Diagnostic Study of Explainability Techniques for Text Classification [52.879658637466605]
We develop a list of diagnostic properties for evaluating existing explainability techniques.
We compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model's performance and the agreement of its rationales with human ones.
arXiv Detail & Related papers (2020-09-25T12:01:53Z)
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.