[Event Preview] Authorship Forensic | 2024 IASLE Webinar Series on Generative AI and Chatbot
date：2024-12-04 17:35author：adminsource：Smart Learning Instituteviews：
2024 IASLE Webinar Series on Generative AI and Chatbot
Topic
Topic
Authorship Forensic
Date and Time:
9 PM-10 PM in GMT+8 on December 18, 2024
9 PM-10 PM in GMT+8 on December 18, 2024
Check for your local time at https://www.timeanddate.com/worldclock/fixedtime.html?iso=20240923T2000&p1=33
Abstract
Over the past several years, we have witnessed the widespread adoption of generative Al Large Language Models such as OpenAl's Generative Pre-Trained Transformer chatbot, ChatGPT. I will introduce a novel approach to authorship attribution our research group has done by leveraging both Statistical Natural Language Processing(SNLP) and Convolutional Neural Networks(CNN) techniques to differentiate between documents written by humans and ChatGPTs.
The proposed 3-stage Authorship Forensics approach trained 2- class (i.e.,human and ChatGPT ) and 3-classi.e.,human, ChatGPT 3.5,and ChatGPT 4) model in a very short time--that is 2-class model is well-trained in less than ONE minute (i.e.,56.82 seconds) and the 3-class model is well-trained in 7 minutes and 26.076 seconds. The results demonstrate a significant ability of the models to distinguish between human and Al-written text, with precision 0.9682 (F0.5 score 0.95) for the 2-class (human and ChatGPT) testing subset and precision 0.9806 (F0.5 score 0.96) in the 3-class (human, ChatGPT 3.5, and ChatGPT 4) testing subset.
Our research group also has the proposed 3-stage Authorship Forensics approach implemented as an open access web application to allow teachers and users to either training their own models or using the existing trained model to get some advice on how the model considers a piece of given text is written by human or AI.
Speaker
Maiga CHANG
Full Professor & Associate Dean, Research & Innovation, Faculty of Science and Technology
Full Professor & Associate Dean, Research & Innovation, Faculty of Science and Technology
Athabasca University
Meeting ID: 859 2474 5657
Passcode: IASLE2024
Free Registration link: https://docs.google.com/forms/d/e/1FAIpQLSfqhZuydCbWXV9Dga2XVKerz8rEAi1inu2svJ0aaGrxuJpUeA/viewform?vc=0&c=0&w=1&flr=0
More info: http://iasle.net/generative-ai-and-chatbot/
This page by Smart Learning Institute of Beijing Normal University is licensed under a Creative Commons Attribution 4.0 International License.