MSc Thesis Proposal Announcement of Jess Joseph Benny:"Evaluation of Large Language Models for Knowledge Informed Fake News Detection"

 

Date: Wednesday April 12th, 2023

Time:  10:30 AM – 12:00 PM

Location: Odette Building, Room 110

 

Reminders: 1. Two-part attendance mandatory (sign-in sheet, QR Code) 2. Arrive 5-10 minutes prior to event starting - LATECOMERS WILL NOT BE ADMITTED. Note that due to demand, if the room has reached capacity, even if you are "early" admission is not guaranteed. 3. Please be respectful of the presenter by NOT knocking on the door for admittance once the door has been closed whether the presentation has begun or not (If the room is at capacity, overflow is not permitted (ie. sitting on floors) as this is a violation of the Fire Safety code). 4. Be respectful of the decision of the advisor/host of the event if you are not given admittance. The School of Computer Science has numerous events occurring soon

 

 

The spread of false or misleading information as news has been a significant threat to governments, organizations and the economy for a long time. However, it has become more prevalent and influential in recent years due to the growing popularity of social media, which is now the primary source of information for more than half of the world’s population. Detecting fake news used to rely mostly on statistical and linguistic analysis of texts, but with the advancement of AI and computer-assisted writing tools, fake news authors can now deceive statistical models. Therefore, more sophisticated methods that use Pre-Trained Language models and Knowledge Graphs have been developed to capture the context and knowledge behind fake news, known as knowledge-informed news classification methods.

 

This research aims to assess how well knowledge-informed fake news classification methods can benefit from large language models (LLMs), such as Google T5, Baidu ERNIE, BERT, etc. In our evaluation, our classification models will be fed with word embeddings generated by large language models, knowledge graph embeddings from WikiData5M Knowledge graph and a few selected statistical features. We will experiment with well-known fake news classification datasets such as FakeNewsNet and COVID-19 Fake News. We expect that our research can provide insights into whether LLMs can enhance the efficacy of knowledge-informed fake news classification methods or whether LLMs can surpass the performance of existing knowledge-informed classification models by themselves.

 

Keywords: Fake News, Large Language Models, Knowledge Graphs, NLP, Deep Learning

 

Internal Reader: Dr. Ikjot Saini        

External Reader: Dr. Yuntong Wang               

Advisor: Dr. Dan Wu