View Proposal

---

Proposer

Ioannis Konstas

Title

NLP - Text Summarisation using Large Language Models

Goal

To build a summarisation system with an LLM

Description

You have most likely already used ChatGPT a few times (or a lot!) Have you ever wondered what it actually takes to build a system based on a Large Language Model (LLM) and evaluate it on a real-world task? In this series of projects (check the rest as well!) we will explore the task of text summarisation. This involves taking a long textual input (it could be a news article, notes, or minutes from an interaction like a meeting, or a dialogue, and converting it into a smaller concise document, or set of bullet points. The important thing is to make sure that the output summary faithfully corresponds to the input while mentioning the most salient/noteworthy points. The idea is to explore several popular techniques for fine-tuning an open-source LLM (e.g., Llama 2) starting from the simpler ones (prompt engineering), all the way up to Parameter Efficient Fine-Tuning (PEFT). We will use standard benchmark datasets and SOTA frameworks to evaluate (and potentially train) our models. We can co-develop the project to emphasise more on the features (conciseness, faithfulness, salience), training, data annotation, or human evaluation.

Resources

Large Language Models, GPU

Background

Machine Learning, NLP (desired: F29AI), software development, F21NL (MSc only), F21CA (MSc only)

Url

Difficulty Level

Challenging

Ethical Approval

None

Number Of Students

1

Supervisor

Ioannis Konstas

Keywords

machine learning, neural networks, large language models, natural language processing (nlp)

Degrees

Bachelor of Science in Computer Science
Master of Science in Artificial Intelligence
Master of Science in Artificial Intelligence with SMI