Fine tuning an LLM for patent drafting

The general objective of this research is to investigate the effectiveness of fine-tuning large language models (LLMs) for the purpose of enhancing patent generation and brainstorming processes across various domains. The project follows an agile project management approach, emphasizing continuous small releases. The project is important to XLSCOUT as it aims to enhance text clustering, mapping and document ranking using advanced technologies like part of speech tagging, named entity recognition and tree-based models. The project will help the trainee in- 1) Providing practical, real-world experience in a specific field. 2) Developing and enhancing a variety of skills, including technical skills related to the industry, as well as soft skills like communication, teamwork, and problem-solving. 3) Networking opportunities as interns will have the chance to connect with professionals in their field, potentially leading to mentorship, job offers, and a broader professional network. 4) Allowing individuals to explore different aspects of a particular industry or career path. This firsthand experience can help interns clarify their career goals and make more informed decisions about their future.

Faculty Supervisor:

Tushar Sharma;Arya Rahgozar

Student:

Partner:

XLSCOUT

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Dalhousie University; University of Ottawa

Program: